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

    Neuronpedia

    INDEX
    Explanations

    changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     risk
    -0.44
    Ӏ
    -0.42
     IDisposable
    -0.41
     cucchiaio
    -0.41
    oleh
    -0.41
     cucchia
    -0.40
     شدم
    -0.39
    ctique
    -0.39
     vPvB
    -0.39
     loss
    -0.39
    POSITIVE LOGITS
     consuls
    0.66
     sceptre
    0.66
    存于互联网档案馆
    0.63
    #+#
    0.63
     Crusoe
    0.63
    ()]
    0.63
     Saxons
    0.63
     coronation
    0.62
    QMetaType
    0.61
    :+:
    0.60
    Act Density 0.088%

    No Known Activations