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

    Neuronpedia

    INDEX
    Explanations

    lists of links/categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egt
    -0.07
    気
    -0.07
    hlas
    -0.07
     Mellon
    -0.06
     خارجی
    -0.06
    отреб
    -0.06
    磁
    -0.06
     potassium
    -0.06
    ضة
    -0.06
    	Title
    -0.06
    POSITIVE LOGITS
    _strlen
    0.08
     Imm
    0.07
     renovations
    0.07
     sculptures
    0.06
     Strategies
    0.06
     Halk
    0.06
     regimes
    0.06
     Initialize
    0.06
     Bal
    0.06
     tips
    0.06
    Act Density 0.010%

    No Known Activations