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

    Neuronpedia

    INDEX
    Explanations

    customer support chatbot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Durchmesser
    0.53
     defeating
    0.46
     ediciones
    0.43
    versing
    0.43
    anjutkan
    0.42
    ığın
    0.42
    kenalkan
    0.41
    threatening
    0.41
    е
    0.41
     derrot
    0.41
    POSITIVE LOGITS
     Adults
    0.45
     adults
    0.43
     Repub
    0.43
     Independ
    0.43
     None
    0.41
     விதி
    0.40
     Mét
    0.40
    CP
    0.39
     Arr
    0.39
    CONTIN
    0.39
    Act Density 0.004%

    No Known Activations