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

    Neuronpedia

    INDEX
    Explanations

    configuration options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     함
    0.29
     revela
    0.27
     História
    0.27
     lucu
    0.26
     विद्यार्थी
    0.26
     Elektrokhimiya
    0.26
     emotionally
    0.26
     Gertrude
    0.26
     Handlung
    0.26
     ا
    0.26
    POSITIVE LOGITS
    Enable
    0.37
    enable
    0.34
    max
    0.34
     enabled
    0.31
    enabled
    0.31
    设置
    0.31
    opaque
    0.31
    protect
    0.30
    force
    0.30
    bypass
    0.30
    Act Density 0.330%

    No Known Activations