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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ag
    -0.07
     etmektedir
    -0.07
     pady
    -0.06
    paginate
    -0.06
    抓
    -0.06
     каб
    -0.06
    cloak
    -0.06
     Conrad
    -0.06
    TypeDef
    -0.06
    /module
    -0.06
    POSITIVE LOGITS
    earned
    0.07
    ملة
    0.07
    luğu
    0.06
    bufio
    0.06
     \
    0.06
     earned
    0.06
     entrusted
    0.06
    stown
    0.06
     conquest
    0.06
     Alex
    0.06
    Act Density 0.066%

    No Known Activations