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

    Neuronpedia

    INDEX
    Explanations

    charset and encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igel
    -0.07
     executable
    -0.06
     accompagn
    -0.06
    熟
    -0.06
     recognizable
    -0.06
    esidir
    -0.06
     scriptures
    -0.06
    poke
    -0.06
     kontakte
    -0.06
    하자
    -0.06
    POSITIVE LOGITS
     biases
    0.06
    olate
    0.06
     Smoking
    0.06
     trailer
    0.06
     thinkers
    0.06
    .atan
    0.06
    .checkbox
    0.06
    ailer
    0.06
    سلام
    0.06
     Callback
    0.06
    Act Density 0.013%

    No Known Activations