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

    Neuronpedia

    INDEX
    Explanations

    application lifecycle methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surround
    -0.07
    ("{}
    -0.07
     prosecutors
    -0.07
     foremost
    -0.07
     folding
    -0.07
    enido
    -0.07
     등록대행
    -0.07
    .nasa
    -0.07
    itates
    -0.07
    uffs
    -0.07
    POSITIVE LOGITS
     getline
    0.07
    StringRef
    0.06
    ]()↵
    0.06
    ="↵
    0.06
    .SetText
    0.06
     {}↵↵↵
    0.06
    ?>"><?
    0.06
    .shape
    0.06
     multiline
    0.06
     etmesi
    0.06
    Act Density 0.004%

    No Known Activations