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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insurg
    -0.06
     च
    -0.06
     garant
    -0.06
     karak
    -0.06
    iddi
    -0.06
     『
    -0.06
     få
    -0.06
     фінанс
    -0.06
     therap
    -0.06
    (filename
    -0.06
    POSITIVE LOGITS
    _CMP
    0.07
     Prompt
    0.06
    utdown
    0.06
    _WH
    0.06
    ``↵
    0.06
    วง
    0.06
     Sing
    0.06
     Judges
    0.06
    LS
    0.06
     operating
    0.06
    Act Density 0.004%

    No Known Activations