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

    Neuronpedia

    INDEX
    Explanations

    moll

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    μές
    -0.07
    -single
    -0.07
     diets
    -0.06
    吴
    -0.06
     Ban
    -0.06
    _AB
    -0.06
    groupon
    -0.06
    "Some
    -0.06
     수가
    -0.06
     subst
    -0.06
    POSITIVE LOGITS
    Link
    0.06
     MOS
    0.06
     ctypes
    0.06
    OPTIONS
    0.06
    Attack
    0.06
    125
    0.06
    表示
    0.06
     distinguishing
    0.06
     replacing
    0.06
     replace
    0.06
    Act Density 0.001%

    No Known Activations