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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    },${
    -0.07
     TYPE
    -0.07
     salope
    -0.06
    throws
    -0.06
     toward
    -0.06
    [self
    -0.06
    çak
    -0.06
    .pag
    -0.06
    czas
    -0.06
     inquire
    -0.06
    POSITIVE LOGITS
    .Hidden
    0.07
    _fast
    0.07
    _feature
    0.07
     Jefferson
    0.06
     farklı
    0.06
     فض
    0.06
     lethal
    0.06
    특
    0.06
     Flux
    0.06
     Orn
    0.06
    Act Density 0.000%

    No Known Activations