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

    Neuronpedia

    INDEX
    Explanations

    technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LR
    -0.08
    .character
    -0.08
    uggle
    -0.08
    -called
    -0.08
     увер
    -0.07
     NCR
    -0.07
    зв
    -0.07
    Symfony
    -0.07
     собственного
    -0.07
     odk
    -0.07
    POSITIVE LOGITS
     Volt
    0.09
     Titel
    0.08
     Pun
    0.08
     Compilation
    0.08
     heilt
    0.08
     pinnacle
    0.07
     Petr
    0.07
     cents
    0.07
     leng
    0.07
     Ond
    0.07
    Act Density 0.004%

    No Known Activations