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

    Neuronpedia

    INDEX
    Explanations

    shell scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verdade
    -0.06
     crush
    -0.06
    ’é
    -0.06
     Jer
    -0.06
    ほ
    -0.06
    .setPreferredSize
    -0.06
    ánchez
    -0.06
    iteration
    -0.06
     userID
    -0.06
    預
    -0.06
    POSITIVE LOGITS
     uğra
    0.07
    차
    0.07
    łem
    0.07
     partnership
    0.06
     withholding
    0.06
    Symbols
    0.06
    めた
    0.06
    lun
    0.06
    ensation
    0.06
    -Line
    0.06
    Act Density 0.001%

    No Known Activations