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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating academic roles and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic departments and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.37
    VideoCapture
    -0.33
     државе
    -0.33
    rad
    -0.31
     behaviour
    -0.30
     кӀош
    -0.30
    lid
    -0.30
     anlam
    -0.29
    ph
    -0.29
     states
    -0.29
    POSITIVE LOGITS
     يتيمه
    0.57
     FACULTY
    0.55
     étoient
    0.53
     newOwner
    0.52
    ſelves
    0.51
    Carriera
    0.51
    SuppressLint
    0.51
     Faculty
    0.50
     interns
    0.49
    нгред
    0.49
    Act Density 0.034%

    No Known Activations