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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (scores
    -0.08
     neural
    -0.07
    entre
    -0.07
     exemption
    -0.07
     Niagara
    -0.07
    一时
    -0.07
    	font
    -0.07
    fault
    -0.07
    Conflict
    -0.06
    胜负
    -0.06
    POSITIVE LOGITS
    ((↵
    0.07
    ﭽ
    0.07
    _DIR
    0.07
     Pacers
    0.07
    (alias
    0.06
    翩
    0.06
     urlparse
    0.06
    .="
    0.06
     BIG
    0.06
    kręc
    0.06
    Act Density 0.051%

    No Known Activations