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

    Neuronpedia

    INDEX
    Explanations

    pain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     جو
    -0.08
    groep
    -0.08
     vault
    -0.07
     awakening
    -0.07
    endors
    -0.07
    Limits
    -0.07
     Omaha
    -0.07
    -toolbar
    -0.07
     narciss
    -0.07
    levator
    -0.07
    POSITIVE LOGITS
     sedation
    0.08
     mutations
    0.08
    用了
    0.08
     deployments
    0.07
     pomoc
    0.07
     opacity
    0.07
    ffff
    0.07
     treatments
    0.07
     workloads
    0.07
     inflammation
    0.07
    Act Density 0.007%

    No Known Activations