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

    Neuronpedia

    INDEX
    Explanations

    known properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extrait
    0.49
    arrage
    0.49
    direito
    0.48
    automobile
    0.48
    orso
    0.47
    orno
    0.47
    curso
    0.47
    amplitude
    0.47
    ਥ
    0.46
     erotic
    0.46
    POSITIVE LOGITS
     popul
    0.49
     Popul
    0.47
     Oct
    0.46
     Shipping
    0.44
     Applies
    0.44
    Popul
    0.44
     Gener
    0.43
     counterparts
    0.43
     Solutions
    0.42
     Essential
    0.42
    Act Density 0.003%

    No Known Activations