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

    Neuronpedia

    INDEX
    Explanations

    frustration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    审计
    -0.08
     accuse
    -0.07
    юсь
    -0.07
     masculinity
    -0.07
    %p
    -0.07
    ID
    -0.07
     mời
    -0.07
     each
    -0.07
    .ms
    -0.07
     himself
    -0.06
    POSITIVE LOGITS
    Updates
    0.08
     entreprene
    0.07
    attern
    0.07
     Jak
    0.07
     PUT
    0.07
    prene
    0.07
     UNIVERS
    0.07
    wor
    0.07
    .Exchange
    0.07
    쨔
    0.07
    Act Density 0.005%

    No Known Activations