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

    Neuronpedia

    INDEX
    Explanations

    Slavery

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    time
    -0.07
    ientes
    -0.07
    lements
    -0.07
    .deltaTime
    -0.07
     drawings
    -0.06
     collaborative
    -0.06
    퓨터
    -0.06
    �
    -0.06
     tah
    -0.06
    cache
    -0.06
    POSITIVE LOGITS
     harb
    0.07
    .int
    0.07
    	sc
    0.06
     una
    0.06
     SSA
    0.06
    收益
    0.06
    cano
    0.06
    .Expressions
    0.06
     Canberra
    0.06
    .ref
    0.06
    Act Density 0.073%

    No Known Activations