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

    Neuronpedia

    INDEX
    Explanations

    metadata and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éroport
    0.52
     பகுதியில்
    0.52
     בית
    0.52
    ibili
    0.51
     بالت
    0.51
     αυτο
    0.50
     трубы
    0.49
     κάνει
    0.49
    ūra
    0.49
     лікар
    0.49
    POSITIVE LOGITS
     Year
    0.52
     Mode
    0.52
     Models
    0.49
     their
    0.47
     Modes
    0.47
    Year
    0.46
    d
    0.46
     dudes
    0.46
     Initial
    0.45
     mediums
    0.45
    Act Density 0.000%

    No Known Activations