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

    Neuronpedia

    INDEX
    Explanations

    various

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    creat
    -0.07
    ора
    -0.06
    VRT
    -0.06
    	throws
    -0.06
    dělení
    -0.06
     silenced
    -0.06
     거의
    -0.06
    ora
    -0.06
    jh
    -0.06
    dy
    -0.06
    POSITIVE LOGITS
    맛
    0.07
     بواسطة
    0.07
    Architecture
    0.07
    boundary
    0.07
     Attempts
    0.07
    segment
    0.07
    _FAILED
    0.06
    _response
    0.06
    _ER
    0.06
    lej
    0.06
    Act Density 0.000%

    No Known Activations