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
    erton
    -0.06
    .isOn
    -0.06
     consultation
    -0.06
    Boxes
    -0.06
    typescript
    -0.06
     chocol
    -0.06
    erin
    -0.06
     été
    -0.06
    Yet
    -0.06
     heure
    -0.06
    POSITIVE LOGITS
    .Errors
    0.07
    =email
    0.06
     zza
    0.06
     recharge
    0.06
    -threatening
    0.06
    icles
    0.06
     mortgage
    0.06
    (detail
    0.06
    =torch
    0.06
     >
    0.06
    Act Density 0.002%

    No Known Activations