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

    Neuronpedia

    INDEX
    Explanations

    pt apt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     switching
    -0.08
     electrode
    -0.07
    variables
    -0.07
     Logs
    -0.07
     を
    -0.07
    	r
    -0.07
     búsqueda
    -0.06
     cycles
    -0.06
    ザー
    -0.06
    قام
    -0.06
    POSITIVE LOGITS
    .await
    0.07
     Knot
    0.06
    lust
    0.06
    licit
    0.06
    .Automation
    0.06
     "-//
    0.06
    pit
    0.06
    236
    0.06
    ัต
    0.06
    ีอย
    0.06
    Act Density 0.006%

    No Known Activations