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

    Neuronpedia

    INDEX
    Explanations

    Mathematics and romance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rie
    -0.87
     utafitiHapana
    -0.60
    Rie
    -0.60
     InputDecoration
    -0.60
    HostException
    -0.59
     مرئيه
    -0.59
    argout
    -0.57
    vignon
    -0.57
    TabIndex
    -0.56
     referenties
    -0.56
    POSITIVE LOGITS
     alko
    0.48
    liel
    0.47
     Affairs
    0.47
    hl
    0.47
    pe
    0.46
    cookieParser
    0.45
     digress
    0.44
    te
    0.43
    ica
    0.43
     AFFAIRS
    0.42
    Act Density 0.059%

    No Known Activations