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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iques
    -0.07
    lech
    -0.07
     về
    -0.07
     кан
    -0.07
    .mp
    -0.06
     photon
    -0.06
    ych
    -0.06
     пож
    -0.06
    -Shirt
    -0.06
     localize
    -0.06
    POSITIVE LOGITS
    。（
    0.06
    rolling
    0.06
    edom
    0.06
    SUMER
    0.06
     subpoena
    0.06
     asi
    0.06
     AIR
    0.06
    adjust
    0.06
    NSMutableArray
    0.06
    multi
    0.06
    Act Density 0.001%

    No Known Activations