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

    Neuronpedia

    INDEX
    Explanations

    changing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lon
    -0.09
    赞叹
    -0.08
    أكثر
    -0.08
    _CONNECT
    -0.08
    EXIT
    -0.07
    -white
    -0.07
    DEPTH
    -0.07
     Calories
    -0.07
    .screen
    -0.07
    Climate
    -0.07
    POSITIVE LOGITS
     hier
    0.07
    ')['
    0.07
    ('-',
    0.07
    航运
    0.07
    _mappings
    0.07
     여기
    0.07
    (instr
    0.07
    ["
    0.07
    '),('
    0.07
     fst
    0.07
    Act Density 0.000%

    No Known Activations