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

    Neuronpedia

    INDEX
    Explanations

    whole

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ić
    -0.07
    ільш
    -0.07
    }s
    -0.07
    argent
    -0.07
     eccentric
    -0.06
    >Password
    -0.06
    icia
    -0.06
    tober
    -0.06
    ocations
    -0.06
     medications
    -0.06
    POSITIVE LOGITS
     whole
    0.13
     Whole
    0.12
    whole
    0.11
    Whole
    0.11
     AppleWebKit
    0.08
     wholly
    0.07
     Coach
    0.07
     throne
    0.07
     Whale
    0.07
     WA
    0.07
    Act Density 0.014%

    No Known Activations