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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.60
     to
    -0.57
    ,
    -0.53
    المكان
    -0.52
    to
    -0.51
    ̍t
    -0.50
     they
    -0.50
    StructEnd
    -0.48
    quam
    -0.48
     also
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.68
     ſmall
    0.65
     autorytatywna
    0.64
     automatiques
    0.63
     chré
    0.63
     ſtate
    0.63
     ſche
    0.63
     courants
    0.62
     chrétien
    0.62
     RIPRODUZIONE
    0.61
    Act Density 0.000%

    No Known Activations