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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ellij
    -0.07
    Vertex
    -0.07
    ̃
    -0.07
     krij
    -0.07
    afa
    -0.06
    -answer
    -0.06
     initiator
    -0.06
     Somali
    -0.06
     kov
    -0.06
     whence
    -0.06
    POSITIVE LOGITS
     정말
    0.07
     suburban
    0.07
    .,↵
    0.06
     огром
    0.06
    _OVERFLOW
    0.06
     nonprofit
    0.06
    Immediately
    0.06
     –↵
    0.06
    酒店
    0.06
     default
    0.06
    Act Density 0.036%

    No Known Activations