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

    Neuronpedia

    INDEX
    Explanations

    second-person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GBT
    -0.07
    _related
    -0.07
     monot
    -0.06
     feel
    -0.06
    (contents
    -0.06
     respectfully
    -0.06
    ,model
    -0.06
    ensex
    -0.06
    Con
    -0.06
    .col
    -0.06
    POSITIVE LOGITS
    ��이
    0.08
    .btnSave
    0.06
     stabbing
    0.06
     skirm
    0.06
    '],
↵
    0.06
     vows
    0.06
    .depend
    0.06
    ripple
    0.06
    ":{"
    0.06
     Anglic
    0.06
    Act Density 0.102%

    No Known Activations