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

    Neuronpedia

    INDEX
    Explanations

    children and family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     withstand
    -0.07
                     ↵
    -0.07
    ()+
    -0.07
    ст
    -0.06
    .footer
    -0.06
     přik
    -0.06
    %f
    -0.06
    PerPage
    -0.06
    STRING
    -0.06
                                    ↵
    -0.06
    POSITIVE LOGITS
     parsley
    0.08
    encer
    0.07
    rying
    0.06
    cult
    0.06
    ências
    0.06
    confirmation
    0.06
    gle
    0.06
     nurturing
    0.06
     ja
    0.06
    نس
    0.06
    Act Density 0.012%

    No Known Activations