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

    Neuronpedia

    INDEX
    Explanations

    consistency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ยก
    -0.07
    _Un
    -0.07
     Pip
    -0.07
    Wild
    -0.07
     che
    -0.07
     offre
    -0.07
     recre
    -0.07
     companyName
    -0.07
     přik
    -0.06
    alborg
    -0.06
    POSITIVE LOGITS
    \helpers
    0.06
    قلال
    0.06
     continual
    0.06
    ,H
    0.06
    rad
    0.06
     Gly
    0.06
     APIs
    0.06
     Guards
    0.06
    ,G
    0.06
    ogeneity
    0.05
    Act Density 0.101%

    No Known Activations