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

    Neuronpedia

    INDEX
    Explanations

    code or number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :T
    -0.07
    ิท
    -0.07
    .leadingAnchor
    -0.07
    Ố
    -0.07
    IST
    -0.06
     coppia
    -0.06
    /Edit
    -0.06
     ji
    -0.06
     corruption
    -0.06
    _ENDIAN
    -0.06
    POSITIVE LOGITS
     optimizations
    0.07
     dlouhodob
    0.07
    _BTN
    0.06
     criticisms
    0.06
    ,...
    0.06
     voting
    0.06
    クション
    0.06
    _create
    0.06
     Techniques
    0.06
     presumably
    0.06
    Act Density 0.015%

    No Known Activations