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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /.
    -0.07
     shl
    -0.06
     것을
    -0.06
    rganization
    -0.06
    치는
    -0.06
    �
    -0.06
    (strcmp
    -0.06
    但
    -0.06
    reminder
    -0.06
    "},
↵
    -0.06
    POSITIVE LOGITS
     Content
    0.08
    pick
    0.07
     testim
    0.07
    (dirname
    0.07
    Cases
    0.07
    anced
    0.07
    dB
    0.07
     Cash
    0.07
    (cd
    0.07
     cette
    0.06
    Act Density 0.005%

    No Known Activations