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

    Neuronpedia

    INDEX
    Explanations

    academic research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beş
    -0.09
    iphertext
    -0.07
    permissions
    -0.07
    atre
    -0.07
     Temple
    -0.06
     MODIFY
    -0.06
    ersistent
    -0.06
    _redirected
    -0.06
     опред
    -0.06
    .normalize
    -0.06
    POSITIVE LOGITS
     clicks
    0.07
    เสร
    0.07
     Công
    0.07
     Dealers
    0.07
    ề
    0.06
     Instruments
    0.06
     olsa
    0.06
     CheckBox
    0.06
    	Connection
    0.06
     midst
    0.06
    Act Density 0.014%

    No Known Activations