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

    Neuronpedia

    INDEX
    Explanations

    those followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แต่
    0.48
     மற்றும்
    0.44
     វា
    0.40
     এটা
    0.39
    <unused543>
    0.39
     pedibusque
    0.36
     これらの
    0.36
     ولكن
    0.36
     ও
    0.35
    eating
    0.35
    POSITIVE LOGITS
     in
    0.67
     of
    0.59
     with
    0.57
     from
    0.54
    在
    0.54
     của
    0.53
     ones
    0.52
     milik
    0.45
     involving
    0.45
     on
    0.44
    Act Density 0.082%

    No Known Activations