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

    Neuronpedia

    INDEX
    Explanations

    mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lety
    -0.07
     इसल
    -0.07
     этой
    -0.07
     kromě
    -0.07
    TO
    -0.06
    �
    -0.06
    otor
    -0.06
    лия
    -0.06
     hasattr
    -0.06
     اوت
    -0.06
    POSITIVE LOGITS
    akukan
    0.07
    骑
    0.07
    ="-
    0.06
    .dm
    0.06
    _',
    0.06
     Derrick
    0.06
    (pow
    0.06
     Bark
    0.06
    ;k
    0.06
     Ann
    0.06
    Act Density 0.003%

    No Known Activations