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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ewan
    -0.08
     cavern
    -0.07
     Beaver
    -0.07
     damp
    -0.07
     beer
    -0.07
    -0.07
     Rahul
    -0.07
     Bever
    -0.07
    Reviewer
    -0.07
    มหานคร
    -0.07
    POSITIVE LOGITS
    102
    0.12
    103
    0.11
    104
    0.10
    101
    0.10
    106
    0.09
    105
    0.09
    107
    0.08
     intelligence
    0.08
     States
    0.07
     Intelligence
    0.07
    Act Density 0.024%

    No Known Activations