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

    Neuronpedia

    INDEX
    Explanations

    obtur/obdur/obliv/verscheuch/mujigae

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    1.48
    AS
    1.25
    .
    1.20
    :
    1.20
     that
    1.19
    ,
    1.18
    UK
    1.10
    /
    1.09
    AV
    1.06
    AND
    1.05
    POSITIVE LOGITS
    <0x93>
    1.06
    <0xA6>
    1.06
    ८
    1.02
    ٨
    1.02
    <0xA1>
    0.99
    را
    0.99
    د
    0.99
    忽略
    0.96
    дем
    0.93
     démarrage
    0.92
    Act Density 0.000%

    No Known Activations