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

    Neuronpedia

    INDEX
    Explanations

    fascinating recent topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suka
    0.43
    稀
    0.42
     riego
    0.41
     एनीमिया
    0.40
     근무
    0.40
    oomla
    0.40
     సంఘ
    0.39
    iolipin
    0.38
    🦴
    0.38
    哪
    0.38
    POSITIVE LOGITS
     Cl
    0.42
     Strat
    0.40
     $<\
    0.40
    strat
    0.39
    ">\
    0.39
     sierpnia
    0.38
     ABSTRACT
    0.38
     Florian
    0.37
    oscill
    0.37
    Abstract
    0.37
    Act Density 0.000%

    No Known Activations