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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the concept of assistance or support

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

    help to enable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    commodations
    -0.55
     Administrativna
    -0.54
     ANSI
    -0.52
     $_"
    -0.52
    enciaga
    -0.52
    ⤹
    -0.51
    feinander
    -0.50
     myſelf
    -0.50
     Quar
    -0.50
    cabulary
    -0.49
    POSITIVE LOGITS
    helps
    0.58
     helps
    0.56
    Helps
    0.47
     Helps
    0.47
    helped
    0.46
    help
    0.46
    NullCheck
    0.43
     ayuda
    0.43
     helped
    0.42
     ensure
    0.42
    Act Density 0.017%

    No Known Activations