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

    Neuronpedia

    INDEX
    Explanations

    others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bouncing
    -0.07
    vale
    -0.07
    ällt
    -0.07
     Christoph
    -0.07
     tiện
    -0.06
     halten
    -0.06
     có
    -0.06
    ABOUT
    -0.06
     Patrol
    -0.06
     preval
    -0.06
    POSITIVE LOGITS
     others
    0.08
     ию
    0.06
     PRI
    0.06
     commented
    0.06
     Κα
    0.06
    ділу
    0.06
    events
    0.06
     Hundreds
    0.05
     antagonist
    0.05
    лей
    0.05
    Act Density 0.006%

    No Known Activations