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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     einmal
    -0.06
    Combat
    -0.06
     enviar
    -0.06
     kara
    -0.06
    rado
    -0.06
     """",↵
    -0.06
    verted
    -0.06
    ливий
    -0.06
    325
    -0.06
     skyline
    -0.06
    POSITIVE LOGITS
     PubMed
    0.07
     Öğren
    0.07
     disruption
    0.07
     reminding
    0.07
     Michele
    0.07
     expr
    0.07
    olume
    0.07
     revisit
    0.06
     spre
    0.06
     harmon
    0.06
    Act Density 0.008%

    No Known Activations