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

    Neuronpedia

    INDEX
    Explanations

    book excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    保险
    -0.06
    стра
    -0.06
     weaknesses
    -0.06
    .ids
    -0.06
    ivors
    -0.06
    े।↵
    -0.06
    ief
    -0.06
    utra
    -0.06
     Кам
    -0.06
     Tone
    -0.06
    POSITIVE LOGITS
    GetString
    0.07
     pelic
    0.07
     flush
    0.06
     recognizes
    0.06
     recipe
    0.06
     клуб
    0.06
    (route
    0.06
     dostan
    0.06
     HC
    0.06
    	Action
    0.06
    Act Density 0.057%

    No Known Activations