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

    Neuronpedia

    INDEX
    Explanations

    ending or leaving

    np_acts-logits-general · gemini-2.5-flash-lite

    Stopping or ending something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.66
    0.65
     powied
    0.61
    お
    0.60
     {
    0.59
    {
    0.59
    '
    0.55
     =
    0.55
    };
    0.53
    ال
    0.52
    POSITIVE LOGITS
    at
    1.15
    ла
    0.96
    as
    0.85
    م
    0.66
    et
    0.64
    ا
    0.60
    yuan
    0.59
    ரான
    0.57
    νο
    0.57
    ње
    0.57
    Act Density 3.750%

    No Known Activations