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

    Neuronpedia

    INDEX
    Explanations

    mathematical and non-English characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    love
    0.41
    leur
    0.41
    listening
    0.40
    hose
    0.39
    calcul
    0.38
    cella
    0.38
    quad
    0.38
    changer
    0.37
    pregn
    0.37
    listener
    0.36
    POSITIVE LOGITS
    ፨
    0.51
     цього
    0.43
    率为
    0.38
     হুমকি
    0.38
     ordinate
    0.38
     ابتدائي
    0.36
    ことがある
    0.36
     Jop
    0.36
    Ꭽ
    0.36
     Sport
    0.35
    Act Density 0.000%

    No Known Activations