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

    Neuronpedia

    INDEX
    Explanations

    put

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .square
    -0.07
    まだ
    -0.06
    okemon
    -0.06
     默认
    -0.06
     mission
    -0.06
     enemies
    -0.06
     está
    -0.06
    สอง
    -0.06
    รรค
    -0.06
    irez
    -0.06
    POSITIVE LOGITS
     put
    0.09
    _TE
    0.07
     plaint
    0.07
    pub
    0.07
    QE
    0.07
    CLAIM
    0.07
    IMPLEMENT
    0.06
    Put
    0.06
     stray
    0.06
    بل
    0.06
    Act Density 0.009%

    No Known Activations