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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modified
    -0.07
     hill
    -0.07
     neural
    -0.06
    _NONE
    -0.06
     dubious
    -0.06
     nervous
    -0.06
     голод
    -0.06
     tòa
    -0.06
    .cards
    -0.06
     Kad
    -0.06
    POSITIVE LOGITS
     Gabri
    0.06
     accuse
    0.06
    <J
    0.06
     httpResponse
    0.06
    .extract
    0.06
     spacecraft
    0.06
    альні
    0.06
     HomeComponent
    0.06
     czy
    0.06
    flammatory
    0.06
    Act Density 0.020%

    No Known Activations