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

    Neuronpedia

    INDEX
    Explanations

    changes and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Deg
    0.40
    getBytes
    0.36
    页
    0.36
    ős
    0.35
     Pil
    0.35
     mocked
    0.35
    emt
    0.35
     적용
    0.35
    érios
    0.35
     ASE
    0.34
    POSITIVE LOGITS
     gable
    0.41
    ルトラ
    0.38
     hinge
    0.38
     obedience
    0.38
    IGER
    0.38
     bombard
    0.37
     postural
    0.37
    einander
    0.37
    specialchars
    0.36
    هد
    0.36
    Act Density 0.000%

    No Known Activations