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

    Neuronpedia

    INDEX
    Explanations

    ating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allowing
    -0.07
    .private
    -0.06
    :g
    -0.06
     Ide
    -0.06
     locker
    -0.06
    円
    -0.06
    _Rect
    -0.06
     Minute
    -0.06
     δ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     punishable
    0.07
    isine
    0.07
     Goldberg
    0.06
    iani
    0.06
     etmeye
    0.06
    zon
    0.06
    esktop
    0.06
    amarin
    0.06
    (JSON
    0.06
    さま
    0.06
    Act Density 0.000%

    No Known Activations