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

    Neuronpedia

    INDEX
    Explanations

    imperfections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esto
    -0.07
     infant
    -0.07
     replicate
    -0.06
     begging
    -0.06
     ту
    -0.06
    udd
    -0.06
     cause
    -0.06
    .bounds
    -0.06
     Subject
    -0.06
     strang
    -0.06
    POSITIVE LOGITS
     AB
    0.07
    。また
    0.06
     CSL
    0.06
    WE
    0.06
     RFC
    0.06
     Açık
    0.06
    
    0.06
    оград
    0.06
    .cvtColor
    0.06
     SP
    0.06
    Act Density 0.046%

    No Known Activations