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

    Neuronpedia

    INDEX
    Explanations

    Division and distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    757
    -0.06
     Afterwards
    -0.06
     место
    -0.06
    ;};↵
    -0.06
     Resets
    -0.06
    _ub
    -0.06
    .getRoot
    -0.06
     Pig
    -0.06
    Alias
    -0.06
     право
    -0.06
    POSITIVE LOGITS
    Water
    0.07
    анная
    0.07
     risks
    0.07
    /tcp
    0.06
    .ncbi
    0.06
    topic
    0.06
    .Headers
    0.06
    _gate
    0.06
    Considering
    0.06
     vive
    0.06
    Act Density 0.005%

    No Known Activations