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

    Neuronpedia

    INDEX
    Explanations

    denying rights, MRI machines, Anna Jarvis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    附近的
    0.52
    ון
    0.46
    恺
    0.46
    ف
    0.46
    颀
    0.46
    itriangular
    0.45
    岖
    0.44
    краё
    0.44
    つけて
    0.43
    ۸
    0.43
    POSITIVE LOGITS
    WE
    0.52
    WRITE
    0.49
    ̀
    0.46
     উহা
    0.44
     chemical
    0.44
     Magic
    0.42
    Magic
    0.42
     kirjo
    0.42
     I
    0.42
     tracing
    0.42
    Act Density 0.000%

    No Known Activations