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

    Neuronpedia

    INDEX
    Explanations

    code/metadata

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     humanities
    -0.07
    	un
    -0.06
    -Encoding
    -0.06
     Take
    -0.06
     miniature
    -0.06
    Unnamed
    -0.06
     Ramadan
    -0.06
    ///////////////////////////////////////////////////////////////////////////////↵
    -0.06
     GUILayout
    -0.06
    phalt
    -0.06
    POSITIVE LOGITS
    -ob
    0.07
    FUL
    0.07
    ساس
    0.07
    في
    0.07
    cedes
    0.06
    ορ
    0.06
    	yield
    0.06
     acceso
    0.06
     infused
    0.06
    letter
    0.06
    Act Density 0.009%

    No Known Activations