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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    apache
    -0.07
     pressed
    -0.07
    bubble
    -0.06
    дается
    -0.06
     س
    -0.06
    -part
    -0.06
     halfway
    -0.06
     espionage
    -0.06
     wurde
    -0.06
    ระเบ
    -0.06
    POSITIVE LOGITS
     pří
    0.07
    agnost
    0.07
    �
    0.07
    .surname
    0.07
    eware
    0.07
    (COLOR
    0.06
     привы
    0.06
    !==
    0.06
    sequently
    0.06
    /backend
    0.06
    Act Density 0.064%

    No Known Activations