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

    Neuronpedia

    INDEX
    Explanations

    answer in form

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟖
    0.60
    顔
    0.54
    ೮
    0.54
    鉐
    0.54
     salir
    0.53
     coriander
    0.52
    ๘
    0.52
    ッティング
    0.52
    довать
    0.52
     RUDDER
    0.52
    POSITIVE LOGITS
    c
    0.60
     D
    0.58
     on
    0.57
     I
    0.57
     En
    0.55
    </b>
    0.53
    D
    0.52
    en
    0.50
    </td>
    0.50
     Sp
    0.50
    Act Density 0.001%

    No Known Activations