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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Terrain
    -0.07
    _commit
    -0.07
     textStatus
    -0.07
    _ENT
    -0.07
    ’ят
    -0.06
    跡
    -0.06
    _ACC
    -0.06
    731
    -0.06
     LIABILITY
    -0.06
     thép
    -0.06
    POSITIVE LOGITS
     number
    0.08
    条件
    0.06
    '";
↵
    0.06
     pee
    0.06
    suming
    0.06
     userProfile
    0.06
    	Json
    0.06
     devour
    0.06
    стр
    0.06
    ú
    0.06
    Act Density 0.006%

    No Known Activations