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

    Neuronpedia

    INDEX
    Explanations

    industrial processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barbati
    -0.75
     auroit
    -0.73
     feroit
    -0.72
     betweenstory
    -0.72
     geox
    -0.71
    expandindo
    -0.70
     pouvoit
    -0.70
     Xunit
    -0.69
     obicei
    -0.67
     CreateTagHelper
    -0.65
    POSITIVE LOGITS
     Fresh
    0.49
     te
    0.48
     fresh
    0.48
     Te
    0.47
     FRESH
    0.46
     val
    0.46
    });*/
    0.44
    localVar
    0.43
     To
    0.42
     wet
    0.42
    Act Density 0.024%

    No Known Activations