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

    Neuronpedia

    INDEX
    Explanations

    boolean values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    이슈
    -0.07
     фут
    -0.06
    nection
    -0.06
    Against
    -0.06
     Toys
    -0.06
     HEL
    -0.06
     incontri
    -0.06
    _SelectedIndexChanged
    -0.06
     Όμιλος
    -0.06
     стек
    -0.06
    POSITIVE LOGITS
    .assertFalse
    0.07
    etection
    0.07
     감
    0.07
    _RM
    0.06
    ekyll
    0.06
     assertTrue
    0.06
    uffer
    0.06
    胆
    0.06
    土
    0.06
    ibern
    0.06
    Act Density 0.022%

    No Known Activations