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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鲅
    -0.08
    ämpfe
    -0.07
    Exchange
    -0.07
    蕰
    -0.07
    ぷ
    -0.07
    ชะ
    -0.07
     executes
    -0.06
    裼
    -0.06
     Fool
    -0.06
    ὠ
    -0.06
    POSITIVE LOGITS
    iros
    0.08
    等行业
    0.07
    利于
    0.07
     critiques
    0.06
    NON
    0.06
     Materials
    0.06
     binary
    0.06
    .util
    0.06
     Astronomy
    0.06
     nn
    0.06
    Act Density 0.004%

    No Known Activations