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

    Neuronpedia

    INDEX
    Explanations

    Chat abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     사업
    -0.07
    ưu
    -0.07
    .JSONArray
    -0.07
     Forces
    -0.06
    ického
    -0.06
    SCRIBE
    -0.06
     "<
    -0.06
     commands
    -0.06
     участи
    -0.06
    

↵
    -0.06
    POSITIVE LOGITS
     haft
    0.07
    _sg
    0.07
    Breadcrumb
    0.07
    (ss
    0.06
    mother
    0.06
     pizza
    0.06
    unfinished
    0.06
     bör
    0.06
     bra
    0.06
    .constructor
    0.06
    Act Density 0.011%

    No Known Activations