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

    Neuronpedia

    INDEX
    Explanations

    normality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >{@
    -0.08
     Jon
    -0.06
     subjects
    -0.06
    .FloatField
    -0.06
    -bre
    -0.06
     '{@
    -0.06
     stringWith
    -0.06
    Sept
    -0.06
     Everywhere
    -0.06
     suicide
    -0.05
    POSITIVE LOGITS
     OMG
    0.07
    usher
    0.07
    ick
    0.06
    Compute
    0.06
     sunglasses
    0.06
    (tol
    0.06
     generously
    0.06
     낮
    0.06
    direccion
    0.06
    INavigation
    0.06
    Act Density 0.011%

    No Known Activations