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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plr
    -0.07
     economically
    -0.07
     análise
    -0.07
    уй
    -0.07
    거나
    -0.06
     algo
    -0.06
    病因
    -0.06
     даже
    -0.06
     stranger
    -0.06
    uação
    -0.06
    POSITIVE LOGITS
     księ
    0.07
    .AP
    0.07
    Given
    0.07
    	size
    0.06
    Speed
    0.06
    三个
    0.06
    秘书长
    0.06
    SSH
    0.06
    HEIGHT
    0.06
    三位
    0.06
    Act Density 0.001%

    No Known Activations