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

    Neuronpedia

    INDEX
    Explanations

    diverse kids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SSID
    0.55
    ଂ
    0.52
     Regierung
    0.52
     Ար
    0.51
     தீ
    0.50
     στις
    0.50
    ಕ್ಕು
    0.50
    ２
    0.50
     Φ
    0.49
     Университе
    0.49
    POSITIVE LOGITS
    models
    0.45
    ing
    0.42
     varieties
    0.42
    features
    0.42
     intellectual
    0.41
     raft
    0.41
     volatiles
    0.41
    field
    0.40
    and
    0.40
    likes
    0.40
    Act Density 0.001%

    No Known Activations