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

    Neuronpedia

    INDEX
    Explanations

    code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashionable
    -0.07
     Determin
    -0.07
    ivid
    -0.07
    .environment
    -0.07
    omnia
    -0.07
     proportions
    -0.07
    uong
    -0.06
     stupidity
    -0.06
     Fon
    -0.06
     중요
    -0.06
    POSITIVE LOGITS
    :pointer
    0.06
    SetBranch
    0.06
    "url
    0.06
    .':
    0.06
     Retrieved
    0.06
    valuation
    0.06
     gang
    0.06
    .ค
    0.05
    deaux
    0.05
    .phi
    0.05
    Act Density 0.056%

    No Known Activations