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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loat
    -0.07
    ",@"
    -0.07
    оги
    -0.07
    -0.06
    иг
    -0.06
     airborne
    -0.06
     "${
    -0.06
     sistemas
    -0.06
    ukkan
    -0.06
    quir
    -0.06
    POSITIVE LOGITS
    (circle
    0.07
     Redskins
    0.07
     rst
    0.06
    ارف
    0.06
     lief
    0.06
    _REUSE
    0.06
     deserved
    0.06
    ))"↵
    0.06
     Pl
    0.06
     crowned
    0.06
    Act Density 0.022%

    No Known Activations