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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Function
    -0.07
    葖
    -0.06
    lua
    -0.06
    在网上
    -0.06
     nichts
    -0.06
    mitter
    -0.06
    Passwords
    -0.06
     kutje
    -0.06
    ตำบ
    -0.06
    מיטב
    -0.06
    POSITIVE LOGITS
    _st
    0.09
     ISO
    0.08
     ["
    0.07
     TH
    0.07
     refining
    0.07
    >";
    0.07
     querying
    0.07
    _eff
    0.07
    🏦
    0.07
    acute
    0.07
    Act Density 0.028%

    No Known Activations