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

    Neuronpedia

    INDEX
    Explanations

    Regular expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Summary
    -0.06
     Activation
    -0.06
    eli
    -0.06
     Curse
    -0.06
    Members
    -0.06
    Solver
    -0.06
    rw
    -0.06
     feasible
    -0.06
     Remove
    -0.06
    adium
    -0.06
    POSITIVE LOGITS
     caval
    0.07
    σκευ
    0.07
     baking
    0.07
    ;line
    0.06
     knock
    0.06
     afflict
    0.06
    ยะ
    0.06
    .once
    0.06
    ','".$
    0.06
    .dispatch
    0.06
    Act Density 0.014%

    No Known Activations