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

    Neuronpedia

    INDEX
    Explanations

    access_key and secret_key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হানি
    0.42
    ޏ
    0.42
    bians
    0.41
    ियां
    0.40
     භ
    0.39
    轳
    0.38
    ށް
    0.38
     parad
    0.38
    盛り
    0.38
    popper
    0.38
    POSITIVE LOGITS
     Comp
    0.41
     बंग
    0.40
     Ophthalm
    0.40
     }[
    0.39
     Download
    0.39
     Dinner
    0.39
     Samsung
    0.38
     iPhone
    0.38
     Gluten
    0.37
     hatte
    0.37
    Act Density 0.000%

    No Known Activations