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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reib
    -0.07
    Operation
    -0.07
     comprehension
    -0.07
    >m
    -0.06
    مین
    -0.06
     cel
    -0.06
     Constantin
    -0.06
     transformer
    -0.06
     nasal
    -0.06
    imagin
    -0.06
    POSITIVE LOGITS
     key
    0.10
     Key
    0.09
    Key
    0.09
    렸다
    0.07
    关键
    0.06
    KEY
    0.06
    akeup
    0.06
     KEY
    0.06
    ;z
    0.06
     keyst
    0.06
    Act Density 0.015%

    No Known Activations