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

    Neuronpedia

    INDEX
    Explanations

    Let me know if you'd like another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parents
    0.65
     jums
    0.64
     financial
    0.62
     collaborate
    0.60
    㔹
    0.60
    "—
    0.59
    迌
    0.58
     sabbatical
    0.58
     debes
    0.58
    financial
    0.58
    POSITIVE LOGITS
    Me
    0.61
    ير
    0.58
    cei
    0.57
    പ്പി
    0.56
    me
    0.55
    inia
    0.55
    يل
    0.55
     Episode
    0.55
    aldehyde
    0.54
    ൂർ
    0.54
    Act Density 0.025%

    No Known Activations