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

    Neuronpedia

    INDEX
    Explanations

    improvement, penalty, element, aberration, atoms, awe, condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অর্চন
    0.37
    FreeFlag
    0.37
    वाड़ा
    0.36
    ậy
    0.36
    ನಾಡ
    0.36
    ༩
    0.36
    ⁦
    0.36
    决心
    0.35
    ་་
    0.35
    ╿
    0.35
    POSITIVE LOGITS
    ↵
    0.40
    oper
    0.36
    q
    0.36
    be
    0.35
     have
    0.35
     Oper
    0.35
     =
    0.35
     Set
    0.35
     oper
    0.34
     He
    0.33
    Act Density 0.000%

    No Known Activations