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

    Neuronpedia

    INDEX
    Explanations

    time, media, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ւ
    0.50
    istice
    0.48
     अटैक
    0.48
    }
    0.45
    }=
    0.45
    
    0.44
     अनुमति
    0.44
     nonsense
    0.43
     Proses
    0.43
    போது
    0.42
    POSITIVE LOGITS
    ﻛ
    0.48
     záb
    0.45
    مد
    0.44
    Andy
    0.44
    كي
    0.43
    كل
    0.43
     cual
    0.42
    İY
    0.41
     inoxyd
    0.41
    MET
    0.41
    Act Density 0.010%

    No Known Activations