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

    Neuronpedia

    INDEX
    Explanations

    time and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বটে
    0.44
     गवर्नमेंट
    0.40
     Srinagar
    0.40
     antipsych
    0.40
    ᱦ
    0.39
     Chevy
    0.39
     Beyoncé
    0.38
    NeedConnect
    0.37
     schizophren
    0.37
     Kashmir
    0.37
    POSITIVE LOGITS
    دس
    0.44
    kovskij
    0.39
     Lebens
    0.38
    opposition
    0.38
    猾
    0.37
    decreasing
    0.37
    აცი
    0.36
     terrasse
    0.36
     flott
    0.36
     cli
    0.35
    Act Density 0.001%

    No Known Activations