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

    Neuronpedia

    INDEX
    Explanations

    Identifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amanda
    -0.07
     Laz
    -0.07
    >s
    -0.07
    #pragma
    -0.07
    stat
    -0.07
    vl
    -0.06
     cambios
    -0.06
    _Stream
    -0.06
     nên
    -0.06
     Wang
    -0.06
    POSITIVE LOGITS
    Identifier
    0.08
    टर
    0.07
    -pre
    0.06
    _Destroy
    0.06
    _fold
    0.06
    _frontend
    0.06
    情
    0.06
    訪
    0.06
    _appro
    0.06
    teness
    0.06
    Act Density 0.001%

    No Known Activations