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

    Neuronpedia

    INDEX
    Explanations

    department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     councillor
    -0.07
    checkBox
    -0.07
     нужно
    -0.07
    bool
    -0.07
    억
    -0.07
    vascular
    -0.07
     COVID
    -0.07
    _POP
    -0.07
    inee
    -0.07
     navigating
    -0.07
    POSITIVE LOGITS
    esch
    0.08
    anny
    0.06
    Uh
    0.06
    惊奇
    0.06
    LIMIT
    0.06
     pr
    0.06
    zn
    0.06
    _DEST
    0.06
    怎么样
    0.06
     motifs
    0.06
    Act Density 0.014%

    No Known Activations