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

    Neuronpedia

    INDEX
    Explanations

    defined by creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forth
    0.52
     বো
    0.40
     Forth
    0.38
     verantwort
    0.37
     unnatural
    0.36
    हो
    0.35
     scalable
    0.35
    FRAME
    0.35
     جان
    0.35
     programmable
    0.35
    POSITIVE LOGITS
     Pok
    0.38
     continually
    0.38
     mainly
    0.37
     isot
    0.36
     masterpieces
    0.35
     creates
    0.35
    Ი
    0.34
     aided
    0.34
    PIRE
    0.34
    LG
    0.33
    Act Density 0.004%

    No Known Activations