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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pageNumber
    -0.07
     pris
    -0.07
    يران
    -0.07
     sermon
    -0.07
    OnChange
    -0.07
     readonly
    -0.07
    (Cl
    -0.06
    ][]
    -0.06
    ([('
    -0.06
    -read
    -0.06
    POSITIVE LOGITS
     dří
    0.07
    .MIN
    0.06
    /mit
    0.06
     Creative
    0.06
    /g
    0.06
    cooldown
    0.06
    _watch
    0.06
    ucked
    0.06
     inst
    0.06
    üy
    0.06
    Act Density 0.002%

    No Known Activations