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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	op
    -0.06
     mới
    -0.06
    .color
    -0.06
     kâ
    -0.06
     Testing
    -0.06
    	to
    -0.06
     chocol
    -0.06
     padding
    -0.06
    �
    -0.06
    &amp
    -0.06
    POSITIVE LOGITS
    Trial
    0.07
     landscapes
    0.07
     observable
    0.07
     Vehicle
    0.07
     Zhang
    0.06
     наблюд
    0.06
     laisse
    0.06
    諸
    0.06
    .skills
    0.06
    Plug
    0.06
    Act Density 0.004%

    No Known Activations