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

    Neuronpedia

    INDEX
    Explanations

    at and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    資格
    0.38
     principally
    0.38
     taxon
    0.37
     morphology
    0.37
     насеко
    0.37
     morphologies
    0.37
     होत्या
    0.36
    ']),
    0.36
     নেতাকর্ম
    0.35
    接
    0.35
    POSITIVE LOGITS
    ാണ
    0.40
     kite
    0.39
    Fore
    0.38
    X
    0.37
     Me
    0.37
     Kite
    0.37
    agg
    0.36
    Sk
    0.36
     Sk
    0.35
     Keine
    0.35
    Act Density 0.000%

    No Known Activations