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

    Neuronpedia

    INDEX
    Explanations

    K

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -arm
    -0.07
    @Test
    -0.07
     μά
    -0.06
     เด
    -0.06
     Portsmouth
    -0.06
    áže
    -0.06
     zoals
    -0.06
     amid
    -0.06
    cısı
    -0.06
    aepernick
    -0.06
    POSITIVE LOGITS
    PERATURE
    0.07
    -fixed
    0.07
     LATIN
    0.07
    intent
    0.07
     Conservative
    0.07
     Universal
    0.07
     Consulting
    0.07
     Research
    0.07
    Experimental
    0.06
    -standard
    0.06
    Act Density 0.001%

    No Known Activations