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

    Neuronpedia

    INDEX
    Explanations

    trace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    改变
    -0.07
    defaultValue
    -0.07
     ~/.
    -0.06
     justo
    -0.06
     affair
    -0.06
    Ju
    -0.06
    	curr
    -0.06
     elevation
    -0.06
    ElementType
    -0.06
     achieving
    -0.06
    POSITIVE LOGITS
    :"
    0.07
    (ps
    0.07
     hateful
    0.07
    ((-
    0.07
     BRO
    0.06
    (ver
    0.06
    =-
    0.06
     bedeut
    0.06
    (bp
    0.06
    Big
    0.06
    Act Density 0.004%

    No Known Activations