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

    Neuronpedia

    INDEX
    Explanations

    descriptions and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सा
    0.50
     wildfires
    0.49
    ח
    0.49
     apenas
    0.48
     đảo
    0.48
    ↵
    0.46
    atilde
    0.45
    ج
    0.45
     ó
    0.45
     implied
    0.45
    POSITIVE LOGITS
     መጠቀም
    0.54
     መጠን
    0.51
     బల
    0.50
    }<\
    0.48
    楎
    0.48
    ⚒
    0.46
     ಕಂಚ
    0.45
     Абра
    0.45
    der
    0.45
    گار
    0.45
    Act Density 0.001%

    No Known Activations