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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Species
    -0.07
    idth
    -0.07
    _,↵
    -0.07
    Blood
    -0.07
     However
    -0.06
     BOOT
    -0.06
    .Static
    -0.06
     뒤
    -0.06
    ))↵↵
    -0.06
    CORE
    -0.06
    POSITIVE LOGITS
    LET
    0.06
    _PRI
    0.06
    msp
    0.06
    Archive
    0.06
     juris
    0.06
     української
    0.06
     cleansing
    0.06
    _typeDefinitionSize
    0.06
     کمی
    0.06
    _IMP
    0.06
    Act Density 0.061%

    No Known Activations