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

    Neuronpedia

    INDEX
    Explanations

    comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    😒
    -0.07
     plight
    -0.07
     unfair
    -0.07
    嘤
    -0.07
    Allocator
    -0.07
     Stacy
    -0.07
     Tiểu
    -0.07
     savory
    -0.07
     Pandora
    -0.07
     matchup
    -0.07
    POSITIVE LOGITS
     grep
    0.07
     Smoking
    0.07
    ез
    0.07
    <len
    0.07
    halten
    0.07
    �
    0.06
    抬起头
    0.06
     BEGIN
    0.06
    냄
    0.06
    Mono
    0.06
    Act Density 0.042%

    No Known Activations