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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    „A
    -0.07
     glBind
    -0.07
     없이
    -0.06
     dct
    -0.06
    elerle
    -0.06
     진짜
    -0.06
     letto
    -0.06
    итет
    -0.06
    .ModelAdmin
    -0.06
     потім
    -0.06
    POSITIVE LOGITS
     Clean
    0.07
    (valid
    0.07
     Ex
    0.07
     Sigma
    0.07
    INDER
    0.06
     sigma
    0.06
    실
    0.06
    _ready
    0.06
    _prot
    0.06
     gestures
    0.06
    Act Density 0.000%

    No Known Activations