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

    Neuronpedia

    INDEX
    Explanations

    Technical/code text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أخرى
    -0.08
    &&
    -0.07
    ��
    -0.07
     جو
    -0.07
     •
    -0.07
    .$.
    -0.07
    umb
    -0.06
    (required
    -0.06
     Externí
    -0.06
    unct
    -0.06
    POSITIVE LOGITS
    šli
    0.07
     zápas
    0.06
    Simply
    0.06
    Miami
    0.06
     Cable
    0.06
     цій
    0.06
    -Semitism
    0.06
    阶段
    0.06
     Until
    0.06
     diapers
    0.06
    Act Density 0.000%

    No Known Activations