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

    Neuronpedia

    INDEX
    Explanations

    intrusive thoughts or imagery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Weitere
    1.55
    ုန်း
    1.24
     تع
    1.23
     Weitere
    1.22
     заве
    1.20
     mettre
    1.19
     tuvieron
    1.19
     ्
    1.17
     Еще
    1.16
    zeum
    1.15
    POSITIVE LOGITS
    호
    1.07
    ors
    1.06
    호를
    1.05
     Apostle
    0.95
    ORS
    0.95
     piecewise
    0.92
    wiek
    0.92
    א
    0.91
    াঙ্গা
    0.90
    Cycles
    0.89
    Act Density 0.000%

    No Known Activations