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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orex
    -0.08
    하게
    -0.07
    .communication
    -0.06
     مار
    -0.06
    似乎
    -0.06
     segregation
    -0.06
    _PRIMARY
    -0.06
    Setup
    -0.06
    Path
    -0.06
     meu
    -0.06
    POSITIVE LOGITS
    connect
    0.07
    ườ
    0.07
    _reader
    0.07
     spoof
    0.07
    080
    0.07
    -building
    0.06
     separat
    0.06
    .userid
    0.06
     cof
    0.06
    .cover
    0.06
    Act Density 0.050%

    No Known Activations