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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    几
    -0.07
     qs
    -0.07
    :event
    -0.07
     CONSEQUENTIAL
    -0.06
    Helmet
    -0.06
    xml
    -0.06
    лек
    -0.06
     folded
    -0.06
    (mapStateToProps
    -0.06
    рук
    -0.06
    POSITIVE LOGITS
     ….
    0.07
    	ff
    0.06
    sei
    0.06
    als
    0.06
    —and
    0.06
     Mostly
    0.06
    ์เน
    0.06
    panion
    0.06
    Ε
    0.06
    できる
    0.06
    Act Density 0.063%

    No Known Activations