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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _basic
    -0.08
    าณาจ
    -0.08
     lớn
    -0.07
    .from
    -0.07
    /course
    -0.06
     Druid
    -0.06
    	ctrl
    -0.06
    §ظ
    -0.06
    	title
    -0.06
     عبد
    -0.06
    POSITIVE LOGITS
    Installed
    0.06
     свій
    0.06
     disclose
    0.06
    滿
    0.06
     unlocks
    0.06
    -clear
    0.06
     peril
    0.06
     surged
    0.06
    大き
    0.06
     heartbeat
    0.06
    Act Density 0.028%

    No Known Activations