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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _record
    -0.07
    31
    -0.07
     cw
    -0.07
     flavors
    -0.06
     Melissa
    -0.06
     brightest
    -0.06
    _tv
    -0.06
    /manage
    -0.06
     tubing
    -0.06
     tobacco
    -0.06
    POSITIVE LOGITS
     Define
    0.07
    .fasterxml
    0.07
    şk
    0.06
     Enhanced
    0.06
    pired
    0.06
    .Is
    0.06
     Cavaliers
    0.06
     asign
    0.06
    \:
    0.06
     ―
    0.06
    Act Density 0.004%

    No Known Activations