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

    Neuronpedia

    INDEX
    Explanations

    Hashing algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _helpers
    -0.07
    Expl
    -0.06
    human
    -0.06
    446
    -0.06
     طی
    -0.06
    ﺎ
    -0.06
    345
    -0.06
    -ground
    -0.06
    Kid
    -0.06
     ldb
    -0.06
    POSITIVE LOGITS
    ')
↵
    0.07
    暴
    0.06
     OT
    0.06
     exporting
    0.06
    лич
    0.06
    销
    0.06
    :'
    0.06
    'er
    0.06
     oh
    0.06
    'e
    0.06
    Act Density 0.016%

    No Known Activations