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

    Neuronpedia

    INDEX
    Explanations

    Microsoft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áze
    -0.06
    OBJ
    -0.06
    .ComboBox
    -0.06
     水
    -0.06
    376
    -0.06
    Finish
    -0.06
     novels
    -0.06
    .Pattern
    -0.06
    _names
    -0.06
    щей
    -0.06
    POSITIVE LOGITS
     pret
    0.07
     svm
    0.06
     Meer
    0.06
     lcm
    0.06
    sonian
    0.06
    Ion
    0.06
     melting
    0.06
     skilled
    0.06
     intestine
    0.06
     م
    0.06
    Act Density 0.001%

    No Known Activations