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

    Neuronpedia

    INDEX
    Explanations

    .Parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mock
    -0.07
     Ade
    -0.06
    xxxx
    -0.06
    ---
    -0.06
     without
    -0.06
    jq
    -0.06
    strong
    -0.05
     Mou
    -0.05
    >
    -0.05
    Or
    -0.05
    POSITIVE LOGITS
    .Parameters
    0.17
    .Entry
    0.09
    .commons
    0.09
     Constantin
    0.08
     Thorn
    0.07
     elkaar
    0.07
    __),
    0.07
    TexParameter
    0.07
    포
    0.07
    .optim
    0.07
    Act Density 0.003%

    No Known Activations