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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	StringBuilder
    -0.07
    톤
    -0.06
    sthrough
    -0.06
     biblical
    -0.06
    (Editor
    -0.06
    .badlogic
    -0.06
    Faculty
    -0.06
    .Subject
    -0.06
     b
    -0.06
     Fourth
    -0.06
    POSITIVE LOGITS
    ench
    0.10
     impuls
    0.08
    orch
    0.07
    Bo
    0.07
    ddy
    0.07
     accessory
    0.07
    oh
    0.07
    osu
    0.07
     advances
    0.07
    人の
    0.06
    Act Density 0.008%

    No Known Activations