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

    Neuronpedia

    INDEX
    Explanations

    third or second in rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secrecy
    1.78
     cryptography
    1.76
    ン
    1.71
    1.66
    ת
    1.63
    1.60
    1.58
    1.55
    1.52
    1.52
    POSITIVE LOGITS
     graders
    2.05
     baseman
    1.91
     grader
    1.75
    ../../
    1.74
    বারের
    1.64
     দফা
    1.60
    ся
    1.57
     fiddle
    1.52
    اً
    1.48
    gameObject
    1.42
    Act Density 0.032%

    No Known Activations