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

    Neuronpedia

    INDEX
    Explanations

    credibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     methodology
    -0.07
     labeling
    -0.07
     boxing
    -0.07
     studio
    -0.07
     extraction
    -0.07
     transmission
    -0.07
    Psi
    -0.07
    ská
    -0.06
    -axis
    -0.06
     box
    -0.06
    POSITIVE LOGITS
    inson
    0.07
    ottesville
    0.07
     trừ
    0.06
    .'),↵
    0.06
     tendr
    0.06
     Dagger
    0.06
     conced
    0.06
    sono
    0.06
    .innerHeight
    0.06
     toast
    0.06
    Act Density 0.020%

    No Known Activations