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

    Neuronpedia

    INDEX
    Explanations

    Ste

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ac
    0.76
     leh
    0.72
    Uc
    0.70
     الدم
    0.70
    umes
    0.69
     MCSF
    0.69
    ியோ
    0.68
    忝
    0.67
    al
    0.67
    LCM
    0.67
    POSITIVE LOGITS
    wing
    0.78
     kayaks
    0.76
     Secret
    0.76
     Magento
    0.76
     Symmetry
    0.74
     メガネ
    0.74
     Dependencies
    0.74
    că
    0.73
     Cosmic
    0.73
    teddy
    0.73
    Act Density 0.000%

    No Known Activations