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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "*"
    -0.07
     selective
    -0.07
    전
    -0.06
    ellen
    -0.06
    achten
    -0.06
     ARC
    -0.06
    /unit
    -0.06
     vlak
    -0.06
     carry
    -0.06
    _neighbor
    -0.06
    POSITIVE LOGITS
    ヴィ
    0.07
    Mc
    0.06
     IPAddress
    0.06
     �
    0.06
    <AM
    0.06
    ائر
    0.06
     Little
    0.06
     Decay
    0.06
    Em
    0.06
     теп
    0.06
    Act Density 0.001%

    No Known Activations