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

    Neuronpedia

    INDEX
    Explanations

    employment related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ult
    -0.07
     τ
    -0.07
     changes
    -0.07
    itle
    -0.07
    Effects
    -0.06
    .Shape
    -0.06
    uncios
    -0.06
    ächst
    -0.06
     spíše
    -0.06
    ometric
    -0.06
    POSITIVE LOGITS
    _DEVICES
    0.07
    -original
    0.06
    imos
    0.06
     вес
    0.06
    �
    0.06
     cancelButton
    0.06
    _AVAILABLE
    0.06
    .undefined
    0.06
     Imper
    0.06
     dh
    0.06
    Act Density 0.003%

    No Known Activations