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
     provisions
    -0.06
    )])
    -0.06
    radio
    -0.06
    '),↵↵
    -0.06
     Constructor
    -0.06
     frozen
    -0.06
    "),↵↵
    -0.06
    grad
    -0.06
     Griffin
    -0.06
     Scripts
    -0.06
    POSITIVE LOGITS
     ihrer
    0.07
     seiner
    0.06
    режд
    0.06
    ched
    0.06
     LINEAR
    0.06
     olmuştur
    0.06
     setEmail
    0.06
     çarp
    0.06
     checkpoints
    0.06
     могу
    0.06
    Act Density 0.090%

    No Known Activations