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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sne
    -0.07
     White
    -0.07
     preempt
    -0.07
    상
    -0.06
    Runnable
    -0.06
    rer
    -0.06
     Naz
    -0.06
     Buk
    -0.06
     getX
    -0.06
    _LIB
    -0.06
    POSITIVE LOGITS
     увелич
    0.07
     barred
    0.07
     definitely
    0.07
     ged
    0.07
    として
    0.06
     improvement
    0.06
     dword
    0.06
    격
    0.06
    _Value
    0.06
    ôt
    0.06
    Act Density 0.004%

    No Known Activations