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

    Neuronpedia

    INDEX
    Explanations

    Motorola

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KeyValue
    -0.07
    Set
    -0.07
     platforms
    -0.07
     unseren
    -0.07
    -0.07
     strengths
    -0.07
    _CONTROLLER
    -0.06
     black
    -0.06
    Main
    -0.06
     refugee
    -0.06
    POSITIVE LOGITS
     Motorola
    0.15
     pierws
    0.07
    ipeline
    0.07
    μιουργ
    0.06
     Moto
    0.06
    tool
    0.06
    πτωση
    0.06
     플
    0.06
     adamant
    0.06
     '%"
    0.06
    Act Density 0.001%

    No Known Activations