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

    Neuronpedia

    INDEX
    Explanations

    Types and versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _entities
    -0.06
    _RF
    -0.06
    ќ
    -0.06
    NOWLED
    -0.06
    ξ
    -0.06
    ัตน
    -0.06
    bate
    -0.06
     paris
    -0.06
    _KERNEL
    -0.06
    _SSL
    -0.06
    POSITIVE LOGITS
    手机号
    0.07
    ues
    0.07
     continuously
    0.07
     seleccion
    0.07
    _lvl
    0.07
     pick
    0.07
    .mul
    0.07
    場
    0.06
     ตอน
    0.06
     vý
    0.06
    Act Density 0.016%

    No Known Activations