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

    Neuronpedia

    INDEX
    Explanations

    broth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     силу
    -0.07
     milit
    -0.06
     energies
    -0.06
    .thread
    -0.06
    êm
    -0.06
     rifles
    -0.06
    ової
    -0.06
     Withdraw
    -0.06
     programme
    -0.06
    irthday
    -0.06
    POSITIVE LOGITS
     broth
    0.08
    OperationContract
    0.07
    (Object
    0.07
     Birch
    0.07
     PCI
    0.06
    KindOfClass
    0.06
     structured
    0.06
     klar
    0.06
    breadcrumbs
    0.06
    $i
    0.06
    Act Density 0.002%

    No Known Activations