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

    Neuronpedia

    INDEX
    Explanations

    Career path

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staircase
    -0.09
     również
    -0.07
    光源
    -0.07
     wheelchair
    -0.07
    诱导
    -0.07
    荠
    -0.07
     Crescent
    -0.07
    磁场
    -0.07
    isContained
    -0.07
     Sutton
    -0.07
    POSITIVE LOGITS
    _conn
    0.07
     suic
    0.07
    _ACK
    0.07
    RI
    0.07
     PDF
    0.06
     usb
    0.06
     exits
    0.06
     Music
    0.06
    scores
    0.06
    조사
    0.06
    Act Density 0.031%

    No Known Activations