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

    Neuronpedia

    INDEX
    Explanations

    acidic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =lambda
    -0.08
    农机
    -0.08
     Nationwide
    -0.07
    憶
    -0.07
    فذ
    -0.07
    采
    -0.07
    海外
    -0.07
    展望
    -0.07
     recounts
    -0.07
    abi
    -0.07
    POSITIVE LOGITS
    𬭳
    0.08
    (it
    0.07
    Gem
    0.07
    消极
    0.07
    _MY
    0.07
    _suffix
    0.07
     Dy
    0.07
     persön
    0.07
     Dog
    0.07
     Yes
    0.07
    Act Density 0.003%

    No Known Activations