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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Antic
    0.38
    мс
    0.38
    ijden
    0.37
    GORITH
    0.37
     língua
    0.37
     Gandh
    0.37
     ½
    0.37
    START
    0.37
    Outcome
    0.37
     Blow
    0.36
    POSITIVE LOGITS
     اليوم
    0.40
    zne
    0.37
    պ
    0.37
    зу
    0.36
    파
    0.36
     ici
    0.36
    純
    0.36
    參
    0.36
     todays
    0.35
    CrL
    0.35
    Act Density 0.002%

    No Known Activations