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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clipse
    -0.07
    (Roles
    -0.07
    (bean
    -0.06
     arrogance
    -0.06
    мир
    -0.06
     Invasion
    -0.06
    范
    -0.06
     Rescue
    -0.06
    ("/
    -0.06
     γνω
    -0.06
    POSITIVE LOGITS
     Palo
    0.07
    ,D
    0.06
    سك
    0.06
    .fi
    0.06
    ront
    0.06
    .M
    0.06
     матери
    0.06
    .K
    0.06
    si
    0.06
     QUEST
    0.06
    Act Density 0.005%

    No Known Activations