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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     på
    -0.07
    �
    -0.06
    альное
    -0.06
     UAE
    -0.06
    sup
    -0.06
     Ün
    -0.06
     barric
    -0.06
    Disable
    -0.06
    ��
    -0.06
     dosy
    -0.06
    POSITIVE LOGITS
     still
    0.07
     серпня
    0.07
    جام
    0.06
    .getLong
    0.06
     αδ
    0.06
     squirrel
    0.06
    SCO
    0.06
     Greenville
    0.06
    elsen
    0.06
     jejichž
    0.06
    Act Density 0.036%

    No Known Activations