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

    Neuronpedia

    INDEX
    Explanations

    Spring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _addresses
    -0.06
     cinema
    -0.06
     recognition
    -0.06
     address
    -0.06
    .modify
    -0.06
    Confirm
    -0.06
     McCabe
    -0.06
    messages
    -0.06
    -domain
    -0.06
    WithError
    -0.06
    POSITIVE LOGITS
    .setParent
    0.06
    �ng
    0.06
     concentration
    0.06
     CoreData
    0.06
     derp
    0.06
     دون
    0.06
    صب
    0.06
    .optString
    0.06
     هند
    0.06
     Hass
    0.06
    Act Density 0.004%

    No Known Activations