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

    Neuronpedia

    INDEX
    Explanations

    shall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    激烈
    -0.07
    ]='
    -0.07
    亲友
    -0.07
    אמי
    -0.07
    info
    -0.07
    okedex
    -0.07
    _Int
    -0.07
     Pool
    -0.07
    ){↵
    -0.06
    withErrors
    -0.06
    POSITIVE LOGITS
     shall
    0.10
    .hpp
    0.07
     excessive
    0.07
    _lookup
    0.07
     paradigm
    0.07
    .respond
    0.07
     HP
    0.07
     Walter
    0.07
     Marshall
    0.07
    😨
    0.07
    Act Density 0.011%

    No Known Activations