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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     therapist
    -0.07
    -var
    -0.07
    -su
    -0.07
     expands
    -0.06
    MES
    -0.06
     мас
    -0.06
     beasts
    -0.06
    _green
    -0.06
     Bond
    -0.06
     generously
    -0.06
    POSITIVE LOGITS
    ï
    0.08
    ilst
    0.07
    USA
    0.06
     キ
    0.06
    střed
    0.06
    чим
    0.06
    ishlist
    0.06
     Rural
    0.06
     밝
    0.06
    γραμμα
    0.06
    Act Density 0.008%

    No Known Activations