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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Recording
    -0.07
    try
    -0.07
    magnitude
    -0.07
    cue
    -0.07
     spéc
    -0.07
     whence
    -0.06
     جان
    -0.06
    ]]:↵
    -0.06
     และ
    -0.06
    osaic
    -0.06
    POSITIVE LOGITS
    llll
    0.06
     осві
    0.06
     surpr
    0.06
     mutil
    0.06
     cabeza
    0.06
     edible
    0.06
     swapped
    0.06
     frequ
    0.06
    しゃ
    0.05
    (','
    0.05
    Act Density 0.003%

    No Known Activations