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
    _bonus
    -0.07
     =========================================================================
    -0.07
    _O
    -0.07
    --------↵↵
    -0.07
     Grandma
    -0.07
     بج
    -0.06
     hjem
    -0.06
     SU
    -0.06
    _throw
    -0.06
     câ
    -0.06
    POSITIVE LOGITS
    ABL
    0.06
     ceremonies
    0.06
     display
    0.06
    ifi
    0.06
     manual
    0.06
    IZATION
    0.06
    .namespace
    0.06
    followers
    0.06
     позвол
    0.06
     法
    0.06
    Act Density 0.000%

    No Known Activations