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

    Neuronpedia

    INDEX
    Explanations

    excuses and justifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    监听
    -0.07
    �
    -0.07
    �
    -0.06
    áh
    -0.06
    독
    -0.06
     limbs
    -0.06
    мест
    -0.06
    ",@"
    -0.06
    Modifiers
    -0.06
     joyful
    -0.06
    POSITIVE LOGITS
     calculated
    0.07
     tactics
    0.06
     SCT
    0.06
     hrad
    0.06
    Reflect
    0.06
     disillusion
    0.06
     Profit
    0.06
     adherence
    0.06
     FOUR
    0.06
     hlas
    0.06
    Act Density 0.140%

    No Known Activations