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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     st
    -0.07
    forcements
    -0.07
     wreak
    -0.06
    ereo
    -0.06
    [++
    -0.06
     اند
    -0.06
     Township
    -0.06
     ic
    -0.06
    RAINT
    -0.06
     chia
    -0.06
    POSITIVE LOGITS
     stabil
    0.07
    .subject
    0.07
     Spect
    0.06
    _DU
    0.06
    Exist
    0.06
    }->
    0.06
     competed
    0.06
     Fluid
    0.06
     alm
    0.06
    akers
    0.05
    Act Density 0.027%

    No Known Activations