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

    Neuronpedia

    INDEX
    Explanations

    Pro

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ғ
    0.68
    aundice
    0.67
    úsc
    0.64
    ikos
    0.62
     perone
    0.62
     bmp
    0.62
    τικό
    0.62
    wet
    0.61
     mcm
    0.61
     itse
    0.61
    POSITIVE LOGITS
     про
    0.97
    Pro
    0.90
    pro
    0.89
     Pro
    0.87
     pro
    0.85
    Про
    0.75
     актив
    0.74
    active
    0.74
    เจ
    0.73
     Про
    0.72
    Act Density 0.028%

    No Known Activations