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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OfYear
    -0.07
    629
    -0.07
     ")";↵
    -0.06
    *******↵
    -0.06
     }↵↵↵↵↵
    -0.06
    ワ
    -0.06
     propos
    -0.06
     outfits
    -0.06
    โก
    -0.06
    .sky
    -0.06
    POSITIVE LOGITS
     clinically
    0.07
     Collider
    0.07
     stimuli
    0.07
    Bl
    0.06
     political
    0.06
    rightarrow
    0.06
     err
    0.06
     study
    0.06
     nd
    0.06
     collider
    0.06
    Act Density 0.038%

    No Known Activations