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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Test
    -0.07
    όμε
    -0.07
    StateMachine
    -0.07
     акку
    -0.07
     test
    -0.06
    (Test
    -0.06
     conhe
    -0.06
     stále
    -0.06
    _sb
    -0.06
     cancelButton
    -0.06
    POSITIVE LOGITS
    -eng
    0.07
     ie
    0.07
     eg
    0.06
    atin
    0.06
     риз
    0.06
    ред
    0.06
     withholding
    0.06
    OutputStream
    0.06
    /templates
    0.06
     adequate
    0.06
    Act Density 0.008%

    No Known Activations