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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chants
    -0.07
     desper
    -0.06
     Disease
    -0.06
    .assert
    -0.06
     bezpečnost
    -0.06
    .isUser
    -0.06
    WORDS
    -0.06
    .identity
    -0.06
     ομά
    -0.06
    Nach
    -0.06
    POSITIVE LOGITS
     Rectangle
    0.07
    aptop
    0.07
    ,obj
    0.06
     pij
    0.06
    -bo
    0.06
    (png
    0.06
    riba
    0.06
    gest
    0.06
    Resolve
    0.06
     Om
    0.06
    Act Density 0.030%

    No Known Activations