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

    Neuronpedia

    INDEX
    Explanations

    rounding math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Build
    -0.07
    -tra
    -0.07
    .getTime
    -0.06
     Operational
    -0.06
    尽管
    -0.06
     drei
    -0.06
    ♕
    -0.06
     Missile
    -0.06
    接地
    -0.06
    -flex
    -0.06
    POSITIVE LOGITS
     mage
    0.07
     NW
    0.07
     Tristan
    0.07
     Samoa
    0.07
     arrivals
    0.07
    iction
    0.07
     Behaviour
    0.06
     enhance
    0.06
     monks
    0.06
    .Back
    0.06
    Act Density 0.001%

    No Known Activations