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

    Neuronpedia

    INDEX
    Explanations

    negative consequence/outcome

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ports
    -0.07
     title
    -0.06
     Dann
    -0.06
     Pharmacy
    -0.06
    info
    -0.06
     observation
    -0.06
     ports
    -0.06
     Treatment
    -0.06
     lighting
    -0.06
     Mu
    -0.06
    POSITIVE LOGITS
     streamline
    0.07
     zk
    0.07
    -BEGIN
    0.07
    -download
    0.06
    likleri
    0.06
     revenue
    0.06
    Cancellation
    0.06
     mxArray
    0.06
    masından
    0.06
     OST
    0.06
    Act Density 0.076%

    No Known Activations