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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seit
    -0.07
     Live
    -0.06
     degli
    -0.06
    %%%%%%%%
    -0.06
    (Some
    -0.06
    .drawLine
    -0.06
     professional
    -0.06
     свою
    -0.06
     sotto
    -0.06
     Fri
    -0.06
    POSITIVE LOGITS
    _PRESS
    0.08
     expire
    0.06
     ming
    0.06
    OURS
    0.06
    installer
    0.06
    acing
    0.06
     Prem
    0.06
    PAD
    0.06
    benhavn
    0.06
    545
    0.06
    Act Density 0.001%

    No Known Activations