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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elle
    -0.07
    圳
    -0.06
    ضوع
    -0.06
     Comparison
    -0.06
     StringField
    -0.06
     calloc
    -0.06
     xmlDoc
    -0.06
     costing
    -0.06
    泊
    -0.06
     Safety
    -0.06
    POSITIVE LOGITS
    endent
    0.07
    DATED
    0.06
     Fle
    0.06
    RuleContext
    0.06
     Original
    0.06
    unos
    0.06
    onomies
    0.06
    |R
    0.06
    lust
    0.06
     ost
    0.06
    Act Density 0.043%

    No Known Activations