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

    Neuronpedia

    INDEX
    Explanations

    Code and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __;
    -0.08
     stimulate
    -0.07
     excuses
    -0.07
    饕
    -0.07
    %(
    -0.07
    流氓
    -0.07
     patron
    -0.07
     отметить
    -0.07
     clustered
    -0.07
     annonce
    -0.07
    POSITIVE LOGITS
    playing
    0.07
    _different
    0.07
    𑘁
    0.07
    TERS
    0.07
           ↵↵
    0.07
    -↵↵
    0.06
    KV
    0.06
    		
↵
↵
    0.06
    .githubusercontent
    0.06
    SSI
    0.06
    Act Density 0.073%

    No Known Activations