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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sculpt
    -0.07
     deprivation
    -0.06
     WebClient
    -0.06
    ляють
    -0.06
     nes
    -0.06
     Ply
    -0.06
     gö
    -0.06
     AAA
    -0.06
     gig
    -0.06
     LRV
    -0.06
    POSITIVE LOGITS
    (result
    0.07
    े-
    0.07
    .party
    0.06
     Prescription
    0.06
    umar
    0.06
    clr
    0.06
    а
    0.06
    ıt
    0.06
     mensen
    0.06
     Img
    0.06
    Act Density 0.005%

    No Known Activations