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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /mock
    -0.07
    _EXPRESSION
    -0.07
     layers
    -0.06
    调整
    -0.06
    cee
    -0.06
    遍
    -0.06
     LO
    -0.06
    NDER
    -0.06
    pections
    -0.06
    _random
    -0.06
    POSITIVE LOGITS
    (Guid
    0.07
    ',)↵
    0.06
     SCM
    0.06
    \"";↵
    0.06
     AJ
    0.06
    _PH
    0.06
    Microsoft
    0.06
    ]];↵↵
    0.06
    *=
    0.06
     ladder
    0.06
    Act Density 0.015%

    No Known Activations