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

    Neuronpedia

    INDEX
    Explanations

    Th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    URIComponent
    -0.08
    u
    -0.07
    URN
    -0.07
     Growing
    -0.07
     of
    -0.07
    比我
    -0.07
    以人为
    -0.07
     Orr
    -0.07
    grow
    -0.07
    emand
    -0.07
    POSITIVE LOGITS
    疤痕
    0.08
     �
    0.08
     th
    0.08
     "\\
    0.07
     wouldn
    0.07
    Validators
    0.07
    _codegen
    0.07
     thermal
    0.07
    发热
    0.07
     Th
    0.07
    Act Density 0.025%

    No Known Activations