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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imers
    -0.08
     stato
    -0.07
    Suppress
    -0.07
     $("#
    -0.06
    割
    -0.06
     arterial
    -0.06
    rms
    -0.06
    intestinal
    -0.06
    consume
    -0.06
    روت
    -0.06
    POSITIVE LOGITS
     ใช
    0.07
    �
    0.06
     decid
    0.06
    mie
    0.06
     Ivy
    0.06
    .TextImageRelation
    0.06
    ndern
    0.06
    etics
    0.06
    ुबह
    0.05
    outside
    0.05
    Act Density 0.100%

    No Known Activations