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

    Neuronpedia

    INDEX
    Explanations

    Code and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     homosexual
    -0.06
     heures
    -0.06
    ;m
    -0.06
     R
    -0.06
    NETWORK
    -0.06
     učitel
    -0.06
    .Network
    -0.06
    .command
    -0.06
     throat
    -0.06
    Christian
    -0.06
    POSITIVE LOGITS
    -margin
    0.07
    อให
    0.06
    ọn
    0.06
    (jq
    0.06
    .unregister
    0.06
    อำ
    0.06
    ้าร
    0.06
    JC
    0.06
    ことも
    0.05
    ength
    0.05
    Act Density 0.029%

    No Known Activations