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
    燃煤
    -0.07
    .exe
    -0.06
    ReadOnly
    -0.06
     FY
    -0.06
    Bed
    -0.06
    荛
    -0.06
    Case
    -0.06
    品德
    -0.06
    _perm
    -0.06
    .ny
    -0.06
    POSITIVE LOGITS
    طار
    0.08
    Hooks
    0.07
    鄂
    0.07
     walkers
    0.07
    Destroyed
    0.07
    Hook
    0.07
    代办
    0.07
     membuat
    0.07
    ersions
    0.07
    elu
    0.06
    Act Density 0.004%

    No Known Activations