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

    Neuronpedia

    INDEX
    Explanations

    Foundation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    502
    -0.07
     Verm
    -0.06
     ServiceProvider
    -0.06
    カー
    -0.06
    (validate
    -0.06
    tor
    -0.06
     tec
    -0.06
     třídy
    -0.06
     explor
    -0.06
     Marvin
    -0.06
    POSITIVE LOGITS
    ịp
    0.07
     matrices
    0.06
    řit
    0.06
    _com
    0.06
     creams
    0.06
     INS
    0.06
    ales
    0.06
     Vet
    0.06
     Nombre
    0.06
     gtk
    0.06
    Act Density 0.001%

    No Known Activations