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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rador
    -0.07
    ernes
    -0.07
    AGER
    -0.07
     ettir
    -0.06
    Han
    -0.06
     olig
    -0.06
    drop
    -0.06
    .Desc
    -0.06
    ienda
    -0.06
     Fem
    -0.06
    POSITIVE LOGITS
     Rolling
    0.07
    Ư�
    0.07
     announc
    0.07
     quantitative
    0.07
     Stones
    0.07
     disturbed
    0.06
     anderen
    0.06
     Flyers
    0.06
    /doc
    0.06
    .Not
    0.06
    Act Density 0.002%

    No Known Activations