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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VIC
    -0.06
     der
    -0.06
    الف
    -0.06
    の人
    -0.06
    Chem
    -0.06
     Rem
    -0.06
     challenger
    -0.06
    一步
    -0.06
    Democratic
    -0.06
     slic
    -0.06
    POSITIVE LOGITS
    ◠
    0.07
    expenses
    0.07
    _icall
    0.07
    bracht
    0.07
    bpp
    0.07
    בסוף
    0.07
    עד
    0.07
    .shop
    0.07
    مسرح
    0.06
    éra
    0.06
    Act Density 0.000%

    No Known Activations