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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imized
    -0.07
    Mate
    -0.06
     EACH
    -0.06
     Compound
    -0.06
     Kiss
    -0.06
    Ranges
    -0.06
    ческим
    -0.06
    _er
    -0.06
     metric
    -0.05
    Credential
    -0.05
    POSITIVE LOGITS
     zásob
    0.07
     trash
    0.07
     finanzi
    0.07
    ่างก
    0.07
    彼
    0.06
    _inactive
    0.06
     guten
    0.06
     Curt
    0.06
     stadiums
    0.06
     průběhu
    0.06
    Act Density 0.269%

    No Known Activations