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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    411
    -0.07
    Transformer
    -0.07
    inq
    -0.07
     contradiction
    -0.06
    姐
    -0.06
    _Ptr
    -0.06
     inconsistent
    -0.06
    _HP
    -0.06
    RN
    -0.06
    (original
    -0.06
    POSITIVE LOGITS
     hanging
    0.08
     plo
    0.07
     mayor
    0.06
    \widgets
    0.06
    Peer
    0.06
     друга
    0.06
     INCIDENTAL
    0.06
    ξε
    0.06
    ागत
    0.06
    sports
    0.06
    Act Density 0.039%

    No Known Activations