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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bedford
    -0.07
     Wallace
    -0.06
     Fang
    -0.06
    288
    -0.06
    848
    -0.06
     calf
    -0.06
    catalog
    -0.06
     Call
    -0.06
     ASF
    -0.06
    leş
    -0.06
    POSITIVE LOGITS
    7
    0.19
     Seven
    0.11
     seven
    0.11
    07
    0.10
    ۷
    0.09
    Seven
    0.09
    5
    0.09
     Snape
    0.08
     j
    0.08
    6
    0.08
    Act Density 0.083%

    No Known Activations