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

    Neuronpedia

    INDEX
    Explanations

    toy unboxing/kids meals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mt
    -0.08
     dialogs
    -0.08
     dialog
    -0.08
     dilakukan
    -0.07
     Consultants
    -0.07
     उम
    -0.07
     consultant
    -0.07
     Barb
    -0.07
    unan
    -0.07
     hablar
    -0.07
    POSITIVE LOGITS
    _inside
    0.10
     acompan
    0.10
    :inline
    0.09
     contained
    0.09
     inside
    0.09
     printed
    0.09
     shipped
    0.09
     accompany
    0.09
     포함
    0.08
     graines
    0.08
    Act Density 0.050%

    No Known Activations