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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sid
    -0.07
     उ
    -0.06
    	ULONG
    -0.06
     minimized
    -0.06
    im
    -0.06
    jd
    -0.06
     sert
    -0.06
    최
    -0.06
    .Act
    -0.06
     Lima
    -0.06
    POSITIVE LOGITS
     TOO
    0.08
    _num
    0.07
    burn
    0.07
    -register
    0.06
     microphone
    0.06
    porn
    0.06
    rst
    0.06
    frei
    0.06
     muzzle
    0.06
    -txt
    0.06
    Act Density 0.064%

    No Known Activations