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

    Neuronpedia

    INDEX
    Explanations

    bone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHIFT
    -0.07
    .Direct
    -0.07
    Password
    -0.06
    息
    -0.06
     Brad
    -0.06
    .gridy
    -0.06
    olid
    -0.06
     Jerry
    -0.06
     участи
    -0.06
     COMP
    -0.06
    POSITIVE LOGITS
     insanely
    0.06
    theorem
    0.06
     FString
    0.06
    _Window
    0.06
    향
    0.06
    _fu
    0.06
    ôme
    0.06
    ={}
    0.06
    apol
    0.06
    approval
    0.06
    Act Density 0.004%

    No Known Activations