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

    Neuronpedia

    INDEX
    Explanations

    illustrates shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poste
    -0.07
     Buffered
    -0.06
    、三
    -0.06
     BIN
    -0.06
     да
    -0.06
     defaultdict
    -0.06
    —with
    -0.06
     filepath
    -0.06
     locationManager
    -0.05
     PAN
    -0.05
    POSITIVE LOGITS
     unrest
    0.07
     washington
    0.07
     viagra
    0.07
     preserve
    0.07
    -content
    0.07
    良い
    0.06
    咨
    0.06
    .touch
    0.06
    .unknown
    0.06
    _that
    0.06
    Act Density 0.007%

    No Known Activations