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

    Neuronpedia

    INDEX
    Explanations

    Institut Department School

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orul
    -1.48
     invito
    -1.45
     arquite
    -1.45
     vence
    -1.44
     professora
    -1.36
     lamenta
    -1.34
    ကိုးက
    -1.34
     fabrica
    -1.34
     chefe
    -1.33
    ಃ
    -1.32
    POSITIVE LOGITS
    -
    1.83
    </u>
    1.83
    /
    1.72
    _
    1.70
    </th>
    1.59
    ,
    1.51
    1.48
    just
    1.41
     Following
    1.41
    at
    1.39
    Act Density 0.012%

    No Known Activations