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
     올
    -0.07
     paying
    -0.06
    posit
    -0.06
    -qu
    -0.06
     Compound
    -0.06
    post
    -0.06
     sea
    -0.06
    _pickle
    -0.06
     прием
    -0.06
    รายงาน
    -0.06
    POSITIVE LOGITS
     伊
    0.07
     Relay
    0.07
    iffe
    0.06
    _charset
    0.06
     mạng
    0.06
     bist
    0.06
    ileges
    0.06
     vx
    0.06
    _td
    0.06
    iture
    0.06
    Act Density 0.000%

    No Known Activations