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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scarlet
    -0.07
     widen
    -0.07
     Breath
    -0.07
    _CELL
    -0.07
     strlen
    -0.07
    Strong
    -0.06
    acro
    -0.06
     nik
    -0.06
     bland
    -0.06
     Gems
    -0.06
    POSITIVE LOGITS
     caus
    0.06
    .boot
    0.06
    老
    0.06
     activities
    0.06
     supposed
    0.06
     purely
    0.06
     Y
    0.06
    phins
    0.06
    柏
    0.06
    issues
    0.06
    Act Density 0.003%

    No Known Activations