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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equation
    -0.07
     Disable
    -0.07
     Erg
    -0.07
     Pride
    -0.06
     流
    -0.06
     Force
    -0.06
    πη
    -0.06
     posture
    -0.06
     Ames
    -0.06
     Liberty
    -0.06
    POSITIVE LOGITS
    igInteger
    0.06
     Mohammad
    0.06
     >&
    0.06
     sucht
    0.06
     Werk
    0.06
    кую
    0.06
    :null
    0.06
    +n
    0.06
    _artist
    0.06
    Accessory
    0.06
    Act Density 0.001%

    No Known Activations