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

    Neuronpedia

    INDEX
    Explanations

    Banking and finance texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discovers
    -0.07
    licable
    -0.07
     Interfaces
    -0.07
    Canadian
    -0.06
    Your
    -0.06
     executable
    -0.06
     điển
    -0.06
     Economy
    -0.06
     presses
    -0.06
    ์ท
    -0.06
    POSITIVE LOGITS
     дав
    0.07
     >>↵↵
    0.07
    (chart
    0.06
     slew
    0.06
     міг
    0.06
     plav
    0.06
    playlist
    0.06
     dispon
    0.06
    .genre
    0.06
     바람
    0.06
    Act Density 0.024%

    No Known Activations