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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raž
    -0.07
    腰
    -0.07
     onSelect
    -0.07
    於
    -0.06
     於
    -0.06
     کردن
    -0.06
     прес
    -0.06
     случай
    -0.06
    �
    -0.06
     technolog
    -0.06
    POSITIVE LOGITS
     relief
    0.07
    Distance
    0.06
    											↵
    0.06
    										↵
    0.06
    characters
    0.06
     Different
    0.06
     Obama
    0.06
    viso
    0.06
                                                ↵
    0.06
                          ↵
    0.06
    Act Density 0.014%

    No Known Activations