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

    Neuronpedia

    INDEX
    Explanations

    before making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ParamNum
    0.43
    uddersfield
    0.43
    uku
    0.42
    ore
    0.42
    汋
    0.41
     pam
    0.40
    oe
    0.40
     Nm
    0.39
    orene
    0.39
     premises
    0.38
    POSITIVE LOGITS
    Inc
    0.41
     الحب
    0.41
     Cipher
    0.41
     الطالب
    0.40
    Cipher
    0.40
    btns
    0.40
     Enc
    0.38
     Cypress
    0.38
     cvec
    0.38
     Cyl
    0.38
    Act Density 0.002%

    No Known Activations