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

    Neuronpedia

    INDEX
    Explanations

    元

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    instance
    -0.08
    Constants
    -0.08
    instances
    -0.08
     Constants
    -0.07
    initial
    -0.07
    responsive
    -0.07
     instance
    -0.07
     Monkey
    -0.07
     चालक
    -0.07
    heavy
    -0.07
    POSITIVE LOGITS
    വിധ
    0.09
     stakeholders
    0.09
     avenues
    0.09
     soorten
    0.09
     entertainment
    0.08
     tegelijk
    0.08
     источ
    0.08
     facets
    0.08
     סוג
    0.08
     аспект
    0.08
    Act Density 0.047%

    No Known Activations