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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    良く
    -0.08
     Trie
    -0.08
    -existent
    -0.07
     commits
    -0.07
     adap
    -0.07
     tmpl
    -0.07
    缭
    -0.07
    spar
    -0.07
    腸
    -0.07
    (inst
    -0.06
    POSITIVE LOGITS
    CES
    0.08
    话语权
    0.07
    所需要的
    0.07
    cej
    0.07
     left
    0.07
    	id
    0.06
    OWN
    0.06
     dancers
    0.06
    座位
    0.06
     defiance
    0.06
    Act Density 0.020%

    No Known Activations