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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    αιδ
    -0.07
    िसम
    -0.07
    Got
    -0.07
     advoc
    -0.07
    ちょ
    -0.07
     Zum
    -0.07
    aramel
    -0.06
     одне
    -0.06
    ümü
    -0.06
    º
    -0.06
    POSITIVE LOGITS
     invitation
    0.08
     utilization
    0.07
     constructions
    0.07
     shutdown
    0.07
     Admiral
    0.07
    .memory
    0.06
    regation
    0.06
    Topology
    0.06
    .createUser
    0.06
     introducing
    0.06
    Act Density 0.000%

    No Known Activations