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

    Neuronpedia

    INDEX
    Explanations

    code, debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weit
    -0.08
    forcing
    -0.07
     kij
    -0.07
     abraz
    -0.07
    -ақ
    -0.07
     forcing
    -0.07
     transplantation
    -0.07
     Allows
    -0.07
     แทง
    -0.07
     Memb
    -0.07
    POSITIVE LOGITS
     assigning
    0.08
     sord
    0.07
    BUG
    0.07
     quid
    0.07
     prostitute
    0.07
     assigned
    0.07
    0.07
     instinct
    0.07
    pun
    0.07
    endre
    0.07
    Act Density 0.000%
    No Known Activations