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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/sentence completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /p
    -0.08
    	p
    -0.08
    (Context
    -0.07
    context
    -0.07
    aco
    -0.07
    -specific
    -0.07
     konkrete
    -0.07
    spotify
    -0.07
     audiobook
    -0.07
    =p
    -0.07
    POSITIVE LOGITS
     chút
    0.08
    �
    0.08
    žete
    0.08
     Cupid
    0.08
     transferred
    0.08
    拆
    0.08
    努
    0.08
    ட்ச
    0.08
    ılıyor
    0.08
    분
    0.07
    Act Density 0.000%

    No Known Activations