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

    Neuronpedia

    INDEX
    Explanations

    packaging and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     træ
    0.41
     morale
    0.41
     ima
    0.39
    toare
    0.38
     agreg
    0.38
    indan
    0.38
     flotation
    0.37
     sAlarm
    0.37
     corps
    0.37
     døde
    0.37
    POSITIVE LOGITS
    【
    0.40
    प्ली
    0.38
    splitter
    0.38
    ）【
    0.38
     EUR
    0.37
    addContainer
    0.37
    】【
    0.36
    carrier
    0.36
    らの
    0.36
    receiver
    0.36
    Act Density 0.006%

    No Known Activations