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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     трохи
    -0.07
     Reggie
    -0.06
     Cannes
    -0.06
    ?key
    -0.06
     ب
    -0.06
     �
    -0.06
     Slide
    -0.06
     lassen
    -0.06
     Orleans
    -0.06
     terrace
    -0.06
    POSITIVE LOGITS
    oram
    0.07
    kul
    0.06
     pure
    0.06
     Rocket
    0.06
    bere
    0.06
    .manage
    0.06
    nev
    0.06
    ρχ
    0.06
     szer
    0.06
    PLIC
    0.06
    Act Density 0.008%

    No Known Activations