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

    Neuronpedia

    INDEX
    Explanations

    numbers or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISING
    0.40
     Kom
    0.39
    Ahmed
    0.39
    อย
    0.38
     empl
    0.38
     Lukas
    0.38
     hik
    0.38
    uluk
    0.38
    STRUCTIONS
    0.38
    पर्स
    0.37
    POSITIVE LOGITS
    wxr
    0.44
    fieldset
    0.38
    ഹാ
    0.37
    tex
    0.36
    ໍ່
    0.36
    تص
    0.36
    arci
    0.35
    ఢ
    0.35
    ண்டிய
    0.35
    ething
    0.34
    Act Density 0.012%

    No Known Activations