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

    Neuronpedia

    INDEX
    Explanations

    advice, recommendations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recordings
    -0.07
     مهند
    -0.06
     teardown
    -0.06
     Deals
    -0.06
     história
    -0.06
     deal
    -0.06
    г
    -0.06
    地球
    -0.06
    /de
    -0.06
     constructing
    -0.06
    POSITIVE LOGITS
     Born
    0.07
     خواب
    0.06
     FontWeight
    0.06
    Toast
    0.06
     juven
    0.06
    owan
    0.06
    اشة
    0.06
    _mail
    0.06
     Bunu
    0.06
     �
    0.06
    Act Density 0.223%

    No Known Activations