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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	job
    -0.07
    \Auth
    -0.06
    ům
    -0.06
     lấy
    -0.06
    ていない
    -0.06
     конечно
    -0.06
     Fabric
    -0.06
    inesis
    -0.06
    GMT
    -0.06
     bazı
    -0.06
    POSITIVE LOGITS
     treating
    0.07
     Social
    0.06
    _database
    0.06
    ceil
    0.06
     declares
    0.06
     Monster
    0.06
    没
    0.06
    -inspired
    0.06
    Jan
    0.06
    urret
    0.06
    Act Density 0.039%

    No Known Activations