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

    Neuronpedia

    INDEX
    Explanations

    issued

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CMS
    -0.06
     EDIT
    -0.06
    要求
    -0.06
    回答
    -0.06
    企業
    -0.06
    696
    -0.06
     gambling
    -0.06
     grille
    -0.06
     GAR
    -0.06
     provided
    -0.06
    POSITIVE LOGITS
    Ending
    0.07
     така
    0.06
    azed
    0.06
    تص
    0.06
    !,↵
    0.06
    Appointment
    0.06
     Ferdinand
    0.06
    .Keys
    0.06
    azes
    0.06
    _pose
    0.06
    Act Density 0.004%

    No Known Activations