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

    Neuronpedia

    INDEX
    Explanations

    Reviews/comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ce
    -0.06
     lives
    -0.06
    .fun
    -0.06
     substring
    -0.06
    solve
    -0.06
     NCAA
    -0.06
    .environment
    -0.06
     todd
    -0.06
     Larson
    -0.05
     occupancy
    -0.05
    POSITIVE LOGITS
     dakika
    0.07
    .currentTimeMillis
    0.07
    hic
    0.06
    ύν
    0.06
     LW
    0.06
    ική
    0.06
     strugg
    0.06
    imachinery
    0.06
     اون
    0.06
    bro
    0.06
    Act Density 0.102%

    No Known Activations