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

    Neuronpedia

    INDEX
    Explanations

    destination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carb
    -0.06
    گیرد
    -0.06
    >Status
    -0.06
    embr
    -0.06
    Dirs
    -0.06
    question
    -0.06
    contro
    -0.06
    .MaximizeBox
    -0.05
    _tags
    -0.05
    ;br
    -0.05
    POSITIVE LOGITS
    _preference
    0.07
     deter
    0.07
     аг
    0.06
    /root
    0.06
    riet
    0.06
     beneficiaries
    0.06
    (Application
    0.06
    amework
    0.06
    _paper
    0.06
    -split
    0.06
    Act Density 0.017%

    No Known Activations