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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of impossibility or absence

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

    Text containing "no"

    np_acts-logits-general · gemini-2.0-flash

    no followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.76
    ValueStyle
    -0.74
    IsMutable
    -0.69
    Personensuche
    -0.68
     Efq
    -0.68
     culturelles
    -0.67
    AsUp
    -0.66
     esternos
    -0.66
     aceea
    -0.65
    قایناق‌لار
    -0.65
    POSITIVE LOGITS
     such
    0.70
     better
    0.69
     reason
    0.58
     no
    0.58
     way
    0.55
    igno
    0.55
     so
    0.53
     denying
    0.51
     easier
    0.51
     worse
    0.51
    Act Density 0.105%

    No Known Activations