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

    Neuronpedia

    INDEX
    Explanations

    handicaps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consultation
    -0.07
     confusion
    -0.07
    Transfer
    -0.07
    395
    -0.07
     discovery
    -0.06
     receipts
    -0.06
     Circuit
    -0.06
     riot
    -0.06
    .mit
    -0.06
    _review
    -0.06
    POSITIVE LOGITS
     handicap
    0.14
     handic
    0.12
    icap
    0.08
     cnt
    0.08
    /*------------------------------------------------
    0.07
    ffset
    0.06
     Sidney
    0.06
    งอย
    0.06
     skinny
    0.06
    .MouseAdapter
    0.06
    Act Density 0.001%

    No Known Activations