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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     develops
    -0.08
    ߕ
    -0.08
    美誉
    -0.07
     einen
    -0.07
    ści
    -0.07
    랖
    -0.07
    これは
    -0.07
    知乎
    -0.07
     uur
    -0.07
    볕
    -0.07
    POSITIVE LOGITS
    utral
    0.07
    -record
    0.07
    _vis
    0.07
    Party
    0.07
    	synchronized
    0.07
    0.07
    <Task
    0.07
     Matte
    0.06
    _stream
    0.06
    _idle
    0.06
    Act Density 0.023%

    No Known Activations