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

    Neuronpedia

    INDEX
    Explanations

    geometrical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocities
    -0.07
     doesn
    -0.07
     userdata
    -0.07
     gathered
    -0.07
     too
    -0.07
    uz
    -0.07
    ii
    -0.07
    .↵↵
    -0.07
     প্রত্য
    -0.07
     low
    -0.07
    POSITIVE LOGITS
     réforme
    0.09
     übr
    0.09
    formes
    0.09
    ו�
    0.09
     جبکہ
    0.09
     restant
    0.09
    FORM
    0.09
    י�
    0.08
    TECH
    0.08
     teine
    0.08
    Act Density 0.127%

    No Known Activations