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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    łu
    -0.10
     Genau
    -0.09
     سرعة
    -0.08
     μεγαλύτε
    -0.08
    _INST
    -0.08
    _initialized
    -0.08
    lestick
    -0.08
     정확
    -0.08
    ення
    -0.08
     semaphore
    -0.08
    POSITIVE LOGITS
     ideas
    0.08
     loved
    0.08
     alternatives
    0.08
     Ideas
    0.08
     lieben
    0.08
     избав
    0.08
     Alternatives
    0.08
     opciones
    0.08
     идеи
    0.08
     Optionen
    0.08
    Act Density 0.018%

    No Known Activations