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

    Neuronpedia

    INDEX
    Explanations

    regular verbs, manual vs automatic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     finding
    0.48
     drawing
    0.46
     namespace
    0.46
     pair
    0.43
    arm
    0.43
     grantor
    0.43
     copy
    0.42
     raised
    0.42
     target
    0.42
     specified
    0.41
    POSITIVE LOGITS
     מ
    0.50
    apanicola
    0.50
    𝗴
    0.50
     violencia
    0.50
    ᥣ
    0.50
    ní
    0.49
     zejména
    0.49
     레
    0.48
     nejen
    0.48
     ಕ್
    0.48
    Act Density 0.002%

    No Known Activations