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

    Neuronpedia

    INDEX
    Explanations

    embarrassing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _management
    -0.06
    996
    -0.06
     perceptions
    -0.06
     continuum
    -0.06
    (IF
    -0.06
     реалізації
    -0.06
    _confirmation
    -0.06
    (conv
    -0.06
    defined
    -0.06
     противоп
    -0.06
    POSITIVE LOGITS
     embarrassing
    0.35
     embarrass
    0.19
     boring
    0.13
     humiliating
    0.12
    arrass
    0.11
     embarrassed
    0.11
     embarrassment
    0.10
     embar
    0.09
     awkward
    0.08
    .DotNetBar
    0.07
    Act Density 0.005%

    No Known Activations