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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     будет
    -0.07
    láv
    -0.07
    _REGISTRY
    -0.07
    ところ
    -0.07
    ,in
    -0.06
    GCC
    -0.06
     Hastings
    -0.06
     fireworks
    -0.06
     위치
    -0.06
     bombing
    -0.06
    POSITIVE LOGITS
    nce
    0.07
    rogram
    0.07
    ################################################################################
    0.06
    ительное
    0.06
     �
    0.06
     informational
    0.06
     statistically
    0.06
     fore
    0.06
     precious
    0.06
    @author
    0.06
    Act Density 0.002%

    No Known Activations