Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the concept of 'being' or 'existence' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    That's [adjective]

    np_acts-logits-general · gemini-2.0-flash

    why not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.78
    principalTable
    -0.69
    وردار
    -0.66
    évaluateur
    -0.65
     referenties
    -0.63
    asteroide
    -0.59
    SharedCtor
    -0.56
    Bioaccumulative
    -0.56
    Controllo
    -0.55
    RepeatedField
    -0.55
    POSITIVE LOGITS
     why
    0.73
    leby
    0.60
     how
    0.55
     coats
    0.55
    halb
    0.52
    oui
    0.52
    ApiModelProperty
    0.51
     Manzan
    0.51
    why
    0.51
    toed
    0.50
    Act Density 0.129%

    No Known Activations