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

    Neuronpedia

    INDEX
    Explanations

    planning documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ipv
    -0.08
    -0.07
    ，那么
    -0.07
     begs
    -0.07
     б
    -0.07
    speaker
    -0.07
     affection
    -0.07
    。那么
    -0.06
    _ipv
    -0.06
    imensional
    -0.06
    POSITIVE LOGITS
    "↵↵↵
    0.10
    >↵↵//
    0.09
    ")↵↵↵
    0.09
    )↵↵//
    0.08
    Ket
    0.08
     Deel
    0.08
    zep
    0.08
    ).↵↵↵
    0.08
    !↵↵↵↵
    0.08
    "↵↵//
    0.08
    Act Density 0.320%
    No Known Activations