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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vz
    -0.07
    _account
    -0.07
     moc
    -0.06
     Ion
    -0.06
    Ion
    -0.06
     ред
    -0.06
     hroz
    -0.06
     Gaming
    -0.06
     entren
    -0.06
    Dev
    -0.06
    POSITIVE LOGITS
    ROUT
    0.06
    ouden
    0.06
     scouts
    0.06
    ."',
    0.06
    زر
    0.06
    erah
    0.06
     reminder
    0.06
    empty
    0.06
    getC
    0.06
    observer
    0.06
    Act Density 0.144%

    No Known Activations