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

    Neuronpedia

    INDEX
    Explanations

    (-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Pow
    -0.07
    desired
    -0.07
    焼
    -0.06
    Pok
    -0.06
     리스트
    -0.06
    TYPE
    -0.06
    URNS
    -0.06
     मण
    -0.06
    _choose
    -0.06
     AUTHORS
    -0.06
    POSITIVE LOGITS
     justices
    0.07
    agal
    0.07
     Sig
    0.07
     bied
    0.07
    bell
    0.06
    582
    0.06
    ll
    0.06
    gene
    0.06
    /java
    0.06
    istle
    0.06
    Act Density 0.004%

    No Known Activations