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

    Neuronpedia

    INDEX
    Explanations

    ST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _logical
    -0.07
     Portug
    -0.07
     Garrett
    -0.07
    ;">
    -0.07
    _extended
    -0.06
    llen
    -0.06
    STONE
    -0.06
    ilmek
    -0.06
     svenska
    -0.06
    ивши
    -0.06
    POSITIVE LOGITS
    ~":"
    0.06
    번호
    0.06
    票
    0.06
     blindly
    0.06
     вари
    0.06
     taxed
    0.06
     Vanilla
    0.06
    .method
    0.06
     injecting
    0.06
    表
    0.06
    Act Density 0.001%

    No Known Activations