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

    Neuronpedia

    INDEX
    Explanations

    first person perspective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unctuation
    -0.07
    .failure
    -0.07
    .refs
    -0.06
    .msg
    -0.06
    \Resources
    -0.06
     freder
    -0.06
     refuge
    -0.06
    InSeconds
    -0.06
     Ø
    -0.06
     competitors
    -0.06
    POSITIVE LOGITS
    -Ass
    0.07
    $_['
    0.06
     dalla
    0.06
     효
    0.06
    북도
    0.06
    ={$
    0.06
     bitmask
    0.06
    bildung
    0.06
    ган
    0.06
    >'.↵
    0.06
    Act Density 0.115%

    No Known Activations