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

    Neuronpedia

    INDEX
    Explanations

    widget, poll, list formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adne
    0.47
    ྟ
    0.44
     लाल
    0.42
     TECHNIQUES
    0.42
    ྨ
    0.42
     serien
    0.41
     Nutzen
    0.41
    ptic
    0.41
    ྣ
    0.41
     Percolation
    0.40
    POSITIVE LOGITS
    OD
    0.51
    ophobia
    0.50
    ików
    0.49
     faz
    0.47
     mourn
    0.47
    agreement
    0.47
     unin
    0.46
    Ο
    0.45
     already
    0.45
    ın
    0.45
    Act Density 0.000%

    No Known Activations