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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verdad
    -0.07
     entry
    -0.06
     operands
    -0.06
    _dtype
    -0.06
     Athen
    -0.06
     リ
    -0.06
    690
    -0.06
     brawl
    -0.06
     vagina
    -0.06
     accountant
    -0.06
    POSITIVE LOGITS
    dration
    0.07
    T
    0.07
    step
    0.06
    Guid
    0.06
    �
    0.06
    ač
    0.06
    pled
    0.06
    lut
    0.06
     Corp
    0.06
    unteer
    0.06
    Act Density 0.002%

    No Known Activations