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

    Neuronpedia

    INDEX
    Explanations

    Legal and compliance issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataSet
    -0.07
     plugins
    -0.07
    )sender
    -0.07
     attractiveness
    -0.06
     uncomfort
    -0.06
     yerde
    -0.06
    <dim
    -0.06
    _swap
    -0.06
    중에
    -0.06
    %).
    -0.06
    POSITIVE LOGITS
    omitempty
    0.08
    currentTime
    0.07
    tron
    0.07
     inconvenience
    0.06
    ANGE
    0.06
     Erdoğan
    0.06
     Modern
    0.06
    ,it
    0.06
     Man
    0.06
    :expr
    0.06
    Act Density 0.137%

    No Known Activations