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

    Neuronpedia

    INDEX
    Explanations

    constructor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PREFIX
    -0.07
     training
    -0.06
     ep
    -0.06
     meaning
    -0.06
    training
    -0.06
     surfing
    -0.06
     urn
    -0.06
    lü
    -0.06
    URN
    -0.06
    _led
    -0.06
    POSITIVE LOGITS
    uder
    0.08
     constructor
    0.08
    _drawer
    0.07
    	constructor
    0.07
    oit
    0.07
    IOR
    0.07
    /result
    0.07
     continuing
    0.07
     Conor
    0.07
    атегор
    0.06
    Act Density 0.003%

    No Known Activations