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

    Neuronpedia

    INDEX
    Explanations

    ¿

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cleanly
    -0.08
     разд
    -0.06
     técn
    -0.06
     коли
    -0.06
     rim
    -0.06
     深
    -0.06
     anál
    -0.06
     하면
    -0.06
     foul
    -0.06
    άνα
    -0.06
    POSITIVE LOGITS
    ์กร
    0.07
    otypes
    0.06
     Pearce
    0.06
     Victims
    0.06
    InMillis
    0.06
     necess
    0.06
     Wins
    0.06
    �
    0.06
    gens
    0.06
    -role
    0.06
    Act Density 0.005%

    No Known Activations