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

    Neuronpedia

    INDEX
    Explanations

    behavior or Douglas Adams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     If
    0.50
    arr
    0.49
    If
    0.48
     That
    0.48
    ording
    0.47
    <>(
    0.47
    she
    0.45
    uigen
    0.45
    uto
    0.45
     let
    0.44
    POSITIVE LOGITS
    CHEMY
    0.51
    ເຄື່ອງ
    0.50
    Ꮡ
    0.49
     INDUSTR
    0.48
    ດີ
    0.48
    鏽
    0.48
     其
    0.47
    ミリー
    0.46
     odorless
    0.46
     }()
    0.46
    Act Density 0.000%

    No Known Activations