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

    Neuronpedia

    INDEX
    Explanations

    processing commands and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     milliards
    0.46
    সাধন
    0.42
     الذ
    0.42
     বিএন
    0.42
     marginalised
    0.42
    bsch
    0.41
     فونبیٹ
    0.41
     आवृ
    0.39
     अराउंड
    0.39
     جانے
    0.39
    POSITIVE LOGITS
    ตำ
    0.44
     Edit
    0.43
     quirk
    0.43
    ⇒
    0.43
    Type
    0.42
    Pre
    0.42
     tweaks
    0.42
    Prefix
    0.41
     edit
    0.41
    Edit
    0.40
    Act Density 0.000%

    No Known Activations