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

    Neuronpedia

    INDEX
    Explanations

    grammar correction: is/are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    U
    0.51
     a
    0.49
    a
    0.49
     statement
    0.47
    H
    0.46
     statements
    0.46
     regions
    0.46
     acceleration
    0.46
    ran
    0.45
    ,
    0.45
    POSITIVE LOGITS
    ктором
    0.57
     домаћин
    0.55
     شرطونو
    0.52
    ків
    0.50
     principios
    0.50
    経済
    0.50
    πί
    0.50
    彠
    0.50
    цима
    0.50
    낫
    0.49
    Act Density 0.005%

    No Known Activations