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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    读
    -0.07
     Fac
    -0.07
     Eq
    -0.07
     Cors
    -0.07
    Odd
    -0.06
    �情
    -0.06
     Append
    -0.06
     hus
    -0.06
     Replace
    -0.06
     ted
    -0.06
    POSITIVE LOGITS
    -half
    0.07
     oyun
    0.07
    950
    0.06
    'a
    0.06
    ’a
    0.06
     sulph
    0.06
    rastructure
    0.06
    .getAction
    0.06
    	background
    0.06
    AILABLE
    0.06
    Act Density 0.018%

    No Known Activations