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

    Neuronpedia

    INDEX
    Explanations

    research findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ufs
    -0.07
     rulers
    -0.07
     providers
    -0.06
    _driver
    -0.06
    /day
    -0.06
     roles
    -0.06
     panties
    -0.06
    atics
    -0.06
    ΩΝ
    -0.06
    SplitOptions
    -0.06
    POSITIVE LOGITS
    	ep
    0.07
     ↵ ↵
    0.06
    confidence
    0.06
     perse
    0.06
     gboolean
    0.06
     azt
    0.06
     ↵↵↵↵↵
    0.06
     『
    0.06
    bool
    0.06
     midfield
    0.06
    Act Density 0.034%

    No Known Activations