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

    Neuronpedia

    INDEX
    Explanations

    Anthony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imon
    -0.07
    Mis
    -0.07
    iteit
    -0.07
    ूल
    -0.07
     Asians
    -0.07
     stirring
    -0.06
    .WebElement
    -0.06
    ilin
    -0.06
    	HashMap
    -0.06
    reservation
    -0.06
    POSITIVE LOGITS
    Anthony
    0.08
     anth
    0.07
     Anthony
    0.07
     hobby
    0.07
     
↵ 
↵
    0.07
    /↵↵↵↵
    0.07
    anst
    0.06
    _eth
    0.06
     marshal
    0.06
     talented
    0.06
    Act Density 0.009%

    No Known Activations