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

    Neuronpedia

    INDEX
    Explanations

    Code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =y
    -0.07
    .scan
    -0.06
    .easing
    -0.06
    swagger
    -0.06
    露
    -0.06
     Mature
    -0.06
    Params
    -0.06
    .shape
    -0.06
    _SIMPLE
    -0.06
     Characters
    -0.06
    POSITIVE LOGITS
     registrations
    0.07
     своего
    0.07
    �
    0.06
    _RTC
    0.06
     MSS
    0.06
    ickou
    0.06
    ظٹ
    0.06
    _lng
    0.06
     writings
    0.06
    .rb
    0.06
    Act Density 0.025%

    No Known Activations