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

    Neuronpedia

    INDEX
    Explanations

    trials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لیس
    -0.07
    �
    -0.07
     herpes
    -0.06
    -google
    -0.06
     Со
    -0.06
     Jose
    -0.06
    产
    -0.06
    	sound
    -0.06
    INDER
    -0.06
    Pane
    -0.06
    POSITIVE LOGITS
    avoid
    0.07
     brink
    0.07
     landing
    0.06
    _;↵
    0.06
    .onStart
    0.06
    .flink
    0.06
     Starting
    0.06
    (datetime
    0.06
     kaliteli
    0.06
    เพลง
    0.06
    Act Density 0.032%

    No Known Activations