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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    off
    -0.07
    Analyzer
    -0.07
     SNMP
    -0.06
    CD
    -0.06
    -off
    -0.06
     notamment
    -0.06
    -transfer
    -0.06
    OFF
    -0.06
     empres
    -0.06
    nh
    -0.06
    POSITIVE LOGITS
     меди
    0.07
     invented
    0.07
    袋
    0.07
     converged
    0.06
     retired
    0.06
    _samples
    0.06
    .decode
    0.06
     sleeps
    0.06
    _pet
    0.06
    Hardware
    0.06
    Act Density 0.009%

    No Known Activations