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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ollapse
    -0.09
    ycling
    -0.09
    OUNTER
    -0.09
    RYPT
    -0.09
    LOUD
    -0.08
    URRENT
    -0.08
    ircle
    -0.08
    ertain
    -0.08
    ycles
    -0.07
    ursors
    -0.07
    POSITIVE LOGITS
     C
    0.10
     Cem
    0.09
     CC
    0.09
     CJ
    0.09
    cab
    0.09
     Cooke
    0.09
     Cave
    0.08
    ,C
    0.08
     Camp
    0.08
    Cream
    0.08
    Act Density 5.009%

    No Known Activations