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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CMS
    -0.07
    _userdata
    -0.06
     *[
    -0.06
    (tuple
    -0.06
     unreachable
    -0.06
     &[
    -0.06
    'R
    -0.06
    TreeView
    -0.06
     Каз
    -0.06
    wrap
    -0.06
    POSITIVE LOGITS
     seine
    0.06
    κι
    0.06
     zone
    0.06
     coff
    0.06
     espresso
    0.06
     Partners
    0.06
     cape
    0.06
    İs
    0.06
    험
    0.06
     вис
    0.06
    Act Density 0.011%

    No Known Activations