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

    Neuronpedia

    INDEX
    Explanations

    Vision statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.49
    𝑵
    0.47
    न
    0.47
     są
    0.46
    עה
    0.45
    ἲ
    0.45
    సూరు
    0.45
    鱧
    0.45
    ัง
    0.45
    Pays
    0.45
    POSITIVE LOGITS
     mistakenly
    0.51
     They
    0.49
     There
    0.46
     contrast
    0.44
     was
    0.44
     T
    0.44
     Dateien
    0.44
     Nietzsche
    0.44
     Someone
    0.43
     Homepage
    0.43
    Act Density 0.000%

    No Known Activations