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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    频
    -0.08
    _numbers
    -0.07
     امکان
    -0.06
    _workers
    -0.06
    _course
    -0.06
    libraries
    -0.06
    lds
    -0.06
    ●●●●●●●●●●●●●●●●
    -0.06
    нитель
    -0.06
     Morr
    -0.06
    POSITIVE LOGITS
     IP
    0.07
    .FILL
    0.07
    ρ
    0.06
    .T
    0.06
     CES
    0.06
    /IP
    0.06
    ATAL
    0.06
    -м
    0.06
    (ll
    0.06
     pesticides
    0.06
    Act Density 0.061%

    No Known Activations