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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hape
    -0.07
     detach
    -0.07
    mart
    -0.07
    .opendaylight
    -0.06
     rotating
    -0.06
     sotto
    -0.06
     chứ
    -0.06
     prominence
    -0.06
    _transactions
    -0.06
    Ul
    -0.06
    POSITIVE LOGITS
     privilege
    0.07
    reported
    0.06
     fucks
    0.06
    Sure
    0.06
    τίου
    0.06
     Algorithms
    0.06
    GRADE
    0.06
    uvre
    0.06
     Instances
    0.06
    .Scope
    0.06
    Act Density 0.002%

    No Known Activations