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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MO
    -0.07
     Petersburg
    -0.07
    won
    -0.07
    (foo
    -0.07
    pcodes
    -0.06
     υπο
    -0.06
    aryana
    -0.06
     Tanz
    -0.06
    鸟
    -0.06
    SX
    -0.06
    POSITIVE LOGITS
    ослав
    0.07
    ्ल
    0.07
     cev
    0.06
     omit
    0.06
     authenticated
    0.06
     С
    0.06
     eag
    0.06
     desenv
    0.06
     Buff
    0.06
    aintenance
    0.06
    Act Density 0.025%

    No Known Activations