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

    Neuronpedia

    INDEX
    Explanations

    general english language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أكبر
    -0.06
     đòi
    -0.06
     Ancak
    -0.06
    ningar
    -0.06
    	This
    -0.06
    ubuntu
    -0.06
    能力
    -0.06
    lerden
    -0.06
    ‌
    -0.06
    -таки
    -0.06
    POSITIVE LOGITS
    turn
    0.08
     Tracks
    0.07
    /front
    0.07
    _CUBE
    0.07
    ritch
    0.07
     brushed
    0.07
    elect
    0.07
     controls
    0.07
    Spark
    0.06
    vin
    0.06
    Act Density 0.000%

    No Known Activations