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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.08
    #ifdef
    -0.07
     {{--<
    -0.07
    _properties
    -0.06
    	freopen
    -0.06
    らの
    -0.06
    看见
    -0.06
    ):
↵
    -0.06
     наяв
    -0.06
    Seek
    -0.06
    POSITIVE LOGITS
    чна
    0.07
    agine
    0.07
    Å
    0.07
    _sm
    0.07
    ength
    0.06
    (Adapter
    0.06
    abase
    0.06
    essenger
    0.06
     habe
    0.06
    ує
    0.06
    Act Density 0.000%

    No Known Activations