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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imulation
    -0.07
     LIN
    -0.06
     ohled
    -0.06
    甜
    -0.06
     Conrad
    -0.06
     lagi
    -0.06
    radius
    -0.06
    ání
    -0.06
    脸
    -0.06
    dealloc
    -0.06
    POSITIVE LOGITS
    xBC
    0.07
     Yugosl
    0.07
     shipped
    0.07
     adopt
    0.06
    ramework
    0.06
     Сан
    0.06
     Sampling
    0.06
     月
    0.06
     computational
    0.06
    _collect
    0.06
    Act Density 0.069%

    No Known Activations