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

    Neuronpedia

    INDEX
    Explanations

    scoring and marks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ately
    0.82
     musically
    0.79
    ANSAS
    0.77
     ان
    0.75
    ígenes
    0.75
     Sasuke
    0.75
    Ah
    0.74
     الخاص
    0.74
    UIButton
    0.74
    istani
    0.74
    POSITIVE LOGITS
     Déc
    0.70
    k
    0.69
     gev
    0.69
     construc
    0.69
     мето
    0.69
    میم
    0.68
     Form
    0.67
     көзге
    0.66
     vorm
    0.66
    action
    0.66
    Act Density 0.000%

    No Known Activations