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

    Neuronpedia

    INDEX
    Explanations

    character substitution/translation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _calibration
    -0.06
     unlikely
    -0.06
    andise
    -0.06
     masks
    -0.06
    бург
    -0.06
    агато
    -0.06
     sqr
    -0.06
    rotch
    -0.06
     ctr
    -0.06
    途
    -0.06
    POSITIVE LOGITS
     <|
    0.07
    ες
    0.06
    *this
    0.06
    全部
    0.06
    ],[-
    0.06
    رس
    0.06
    425
    0.06
    /result
    0.06
     Effect
    0.06
    isRequired
    0.06
    Act Density 0.008%

    No Known Activations