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

    Neuronpedia

    INDEX
    Explanations

    reductions and simplifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiếng
    -0.07
    ARTH
    -0.07
     AM
    -0.07
     meld
    -0.07
     garnered
    -0.07
    actionDate
    -0.06
    .FLOAT
    -0.06
    ong
    -0.06
     LIGHT
    -0.06
     doorway
    -0.06
    POSITIVE LOGITS
     Kid
    0.07
    кс
    0.06
    getDrawable
    0.06
     '}
    0.06
    -heading
    0.06
     paren
    0.06
     cro
    0.06
     diets
    0.06
    bt
    0.06
     fancy
    0.06
    Act Density 0.001%

    No Known Activations