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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “I
    -0.06
    �
    -0.06
    gers
    -0.06
     diamonds
    -0.06
     nop
    -0.06
    !--
    -0.06
     campuses
    -0.06
     pinpoint
    -0.06
    Ar
    -0.06
    scope
    -0.06
    POSITIVE LOGITS
    CastException
    0.08
    _BUILD
    0.07
     помог
    0.07
     осві
    0.06
    _STAGE
    0.06
     incentiv
    0.06
    (Packet
    0.06
    marketing
    0.06
     LoginForm
    0.06
     brib
    0.06
    Act Density 0.004%

    No Known Activations