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

    Neuronpedia

    INDEX
    Explanations

    weight loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     χρον
    -0.07
    WF
    -0.07
    hetti
    -0.07
     över
    -0.07
     WF
    -0.07
     PSD
    -0.07
     HEAD
    -0.07
     Heads
    -0.07
     covariance
    -0.07
    -0.07
    POSITIVE LOGITS
     снижение
    0.10
     transpl
    0.09
     restructure
    0.09
     transplant
    0.09
    Published
    0.09
     verminderen
    0.09
     verwijderen
    0.08
     profound
    0.08
     placebo
    0.08
    Chaque
    0.08
    Act Density 0.013%
    No Known Activations