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

    Neuronpedia

    INDEX
    Explanations

    Misinformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fair
    0.41
     Fair
    0.40
     FAIR
    0.37
    ến
    0.36
    alt
    0.36
     Alt
    0.36
     неизвест
    0.36
    дя
    0.35
    αλ
    0.35
    
    0.35
    POSITIVE LOGITS
     mis
    0.61
    Mis
    0.57
     Mis
    0.55
     conceptions
    0.51
    ery
    0.49
    mis
    0.46
     conceptual
    0.45
     काफ़ी
    0.45
     concepto
    0.45
     MIS
    0.44
    Act Density 0.007%

    No Known Activations