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

    Neuronpedia

    INDEX
    Explanations

    closest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .DropDownItems
    -0.07
     шах
    -0.06
     politics
    -0.06
    .ColumnStyles
    -0.06
    现代
    -0.06
    須
    -0.06
    fi
    -0.06
    ume
    -0.06
     chimney
    -0.06
     Fer
    -0.06
    POSITIVE LOGITS
     closest
    0.21
    closest
    0.12
    .closest
    0.08
    expiration
    0.07
     destroys
    0.07
    (snapshot
    0.06
    _elapsed
    0.06
     Paw
    0.06
    aría
    0.06
     THR
    0.06
    Act Density 0.002%

    No Known Activations