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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     awe
    -0.07
     gram
    -0.06
     hội
    -0.06
    ób
    -0.06
    claimer
    -0.06
    Tank
    -0.06
    arkan
    -0.06
    _mock
    -0.06
    áků
    -0.06
    elda
    -0.06
    POSITIVE LOGITS
     fontWithName
    0.07
    =[];↵
    0.07
     ''
↵
    0.06
    /**
↵
    0.06
    _HERSHEY
    0.06
     руковод
    0.06
    =[]
↵
    0.06
    (grad
    0.06
     localtime
    0.06
     #
↵
    0.06
    Act Density 0.003%

    No Known Activations