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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intValue
    -0.07
    getAll
    -0.06
    .synthetic
    -0.06
     здійснення
    -0.06
     Seven
    -0.06
    リン
    -0.06
     abstraction
    -0.06
    .has
    -0.06
    дром
    -0.06
     ×
    -0.06
    POSITIVE LOGITS
     Buddy
    0.07
    �
    0.07
    َق
    0.07
    -base
    0.07
     vandalism
    0.07
    neighbor
    0.07
    A
    0.07
    ้
    0.07
     space
    0.06
     něm
    0.06
    Act Density 0.011%

    No Known Activations