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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lfw
    -0.07
     Parents
    -0.06
    apis
    -0.06
     Tư
    -0.06
     robot
    -0.06
     SUN
    -0.06
    Σ
    -0.06
    _sz
    -0.06
     HW
    -0.06
    terminal
    -0.06
    POSITIVE LOGITS
     Hazard
    0.07
     Bruno
    0.06
    �
    0.06
    lemek
    0.06
     Pradesh
    0.06
    _comment
    0.06
     asker
    0.06
     Jessica
    0.06
    	Iterator
    0.06
    _optional
    0.06
    Act Density 0.158%

    No Known Activations