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

    Neuronpedia

    INDEX
    Explanations

    until fragrant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.35
    9
    0.34
    3
    0.32
    4
    0.32
     Metro
    0.30
    6
    0.29
     w
    0.29
     Tourism
    0.29
     Symphony
    0.29
     Symph
    0.27
    POSITIVE LOGITS
    inded
    0.30
    ពួកគេ
    0.28
    ppure
    0.28
    PropertyGroup
    0.27
     exercised
    0.27
    ῖς
    0.27
    ревно
    0.27
     reimbursed
    0.27
    歿
    0.27
     liable
    0.27
    Act Density 0.002%

    No Known Activations