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

    Neuronpedia

    INDEX
    Explanations

    possibility or suggestion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meat
    -0.07
     Trev
    -0.06
     Z
    -0.06
     двох
    -0.06
     TOR
    -0.06
    NSUInteger
    -0.06
     Ibn
    -0.06
    Rua
    -0.06
    -0.06
     Spect
    -0.05
    POSITIVE LOGITS
    ри
    0.07
     mio
    0.07
     validator
    0.07
     extreme
    0.07
     Duffy
    0.06
    YLE
    0.06
    ило
    0.06
    .exception
    0.06
    lluminate
    0.06
     createAction
    0.06
    Act Density 0.031%

    No Known Activations