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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     根
    -0.07
    QPCP
    -0.07
     güney
    -0.07
    ape
    -0.07
    getNode
    -0.07
    €€€€
    -0.06
     gözlem
    -0.06
     Uygu
    -0.06
    nutí
    -0.06
    _member
    -0.06
    POSITIVE LOGITS
    μον
    0.07
     Just
    0.07
     crisis
    0.07
    Â
    0.07
     shot
    0.06
    -fat
    0.06
    τσ
    0.06
    ­t
    0.06
    otch
    0.06
    "):
    0.06
    Act Density 0.066%

    No Known Activations