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

    Neuronpedia

    INDEX
    Explanations

    road leads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Self
    0.55
     Self
    0.49
     आत्म
    0.47
    model
    0.47
    7
    0.46
    مل
    0.46
    Large
    0.46
     После
    0.45
    视图
    0.44
    आत्म
    0.44
    POSITIVE LOGITS
    𒇽
    0.45
     honti
    0.45
     ilk
    0.44
    IPE
    0.43
    fathers
    0.43
     elevationMap
    0.43
    🏨
    0.43
    pellier
    0.42
     impediments
    0.42
     disturbs
    0.42
    Act Density 0.003%

    No Known Activations