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

    Neuronpedia

    INDEX
    Explanations

    fees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Americans
    -0.07
    Foo
    -0.06
     schools
    -0.06
     Dwight
    -0.06
     Fitz
    -0.06
    ilege
    -0.06
    Fair
    -0.06
    ])
    -0.06
     Atmospheric
    -0.06
    ')↵↵
    -0.06
    POSITIVE LOGITS
    POSE
    0.06
     활
    0.06
    ,pos
    0.06
    肌
    0.06
    -break
    0.06
     praying
    0.06
    ,retain
    0.06
     вст
    0.06
    <Service
    0.06
    -items
    0.06
    Act Density 0.022%

    No Known Activations