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

    Neuronpedia

    INDEX
    Explanations

    Conversations and instructions

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     SAME
    -0.08
    ,
    -0.07
     DET
    -0.07
    “Yes
    -0.07
    潦
    -0.07
    	Value
    -0.07
    됴
    -0.07
    _RETURN
    -0.07
     guilty
    -0.07
    Mad
    -0.07
    POSITIVE LOGITS
     platforms
    0.08
    وفر
    0.07
    authorize
    0.07
    iciar
    0.07
     users
    0.07
     processor
    0.07
     компьютер
    0.07
    light
    0.07
    成就感
    0.07
    */
    0.07
    Act Density 0.794%

    No Known Activations