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

    Neuronpedia

    INDEX
    Explanations

    steganography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แดง
    -0.07
     instantaneous
    -0.07
    Ð
    -0.07
     LAS
    -0.07
    Various
    -0.06
    ΑΙ
    -0.06
    (always
    -0.06
    ('~
    -0.06
     Wedding
    -0.06
    Dear
    -0.06
    POSITIVE LOGITS
     شی
    0.06
     planes
    0.06
    iq
    0.06
    ريب
    0.06
     scooter
    0.06
    に関する
    0.06
    ico
    0.06
     wrestlers
    0.06
     Karen
    0.06
    ен
    0.06
    Act Density 0.007%

    No Known Activations