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

    Neuronpedia

    INDEX
    Explanations

    mascara and eyelashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diets
    -0.07
     Logan
    -0.06
    ');?></
    -0.06
     показ
    -0.06
    "))↵↵
    -0.06
     dbo
    -0.06
    .Some
    -0.06
    те
    -0.06
    _floor
    -0.06
     Orientation
    -0.06
    POSITIVE LOGITS
     constitutional
    0.07
     듯
    0.07
    attack
    0.07
    нес
    0.06
     strawberry
    0.06
     státní
    0.06
    /add
    0.06
    guided
    0.06
     Canterbury
    0.06
    adf
    0.06
    Act Density 0.040%

    No Known Activations