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

    Neuronpedia

    INDEX
    Explanations

    sec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脐
    -0.07
    饵
    -0.07
     childbirth
    -0.07
     перед
    -0.07
    楮
    -0.07
    ☽
    -0.07
     Ionic
    -0.07
     '{$
    -0.07
     Cry
    -0.07
    Չ
    -0.07
    POSITIVE LOGITS
     saves
    0.07
    '):↵
    0.07
    ",↵
    0.07
    省
    0.07
     wide
    0.07
    iversity
    0.07
     зависим
    0.06
    	model
    0.06
     Sustainable
    0.06
    \xaa
    0.06
    Act Density 0.000%

    No Known Activations