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

    Neuronpedia

    INDEX
    Explanations

    electric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     atm
    -0.07
     arasındaki
    -0.06
     restores
    -0.06
    iline
    -0.06
    ворю
    -0.06
     magnets
    -0.06
     concat
    -0.06
    estatus
    -0.06
    .splitext
    -0.06
    POSITIVE LOGITS
    .ac
    0.07
    rı
    0.06
     Admir
    0.06
     demonstr
    0.06
    Permanent
    0.06
    .optional
    0.06
     acess
    0.06
    さらに
    0.05
    :!
    0.05
    ‐‐
    0.05
    Act Density 0.005%

    No Known Activations