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

    Neuronpedia

    INDEX
    Explanations

    Caterpillar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NI
    0.42
     cry
    0.40
     SI
    0.40
    NDE
    0.39
    SI
    0.39
    NI
    0.39
     sideWeight
    0.39
     th
    0.38
     hierarch
    0.38
    aronne
    0.38
    POSITIVE LOGITS
    ysters
    0.38
    стики
    0.36
    ertas
    0.36
    वरों
    0.35
    ढ़
    0.35
     неза
    0.35
    akkhand
    0.35
    vény
    0.35
     ہوتی
    0.34
    氮
    0.34
    Act Density 0.000%

    No Known Activations