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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ynes
    -0.08
    .qty
    -0.07
     Request
    -0.07
    agrant
    -0.07
    itchens
    -0.07
    myModal
    -0.06
     assessed
    -0.06
     prostitutas
    -0.06
    ASSERT
    -0.06
     witnessed
    -0.06
    POSITIVE LOGITS
    凯
    0.08
    -I
    0.07
    Hibernate
    0.06
    Spell
    0.06
    ческая
    0.06
    eyim
    0.06
    (create
    0.06
    243
    0.06
    741
    0.06
    ственный
    0.06
    Act Density 0.000%

    No Known Activations