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

    Neuronpedia

    INDEX
    Explanations

    prior art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prior
    -0.66
    Prior
    -0.59
    <eos>
    -0.55
     Al
    -0.55
    al
    -0.52
    y
    -0.50
    /
    -0.50
    ↵↵
    -0.50
     $\
    -0.50
    ,
    -0.49
    POSITIVE LOGITS
     Majefty
    1.52
     Efq
    1.37
     houſe
    1.34
     Houſe
    1.27
     purpoſe
    1.27
     Jefus
    1.24
     myſelf
    1.24
     Theſe
    1.23
     ſtate
    1.22
     pleaſure
    1.22
    Act Density 0.335%

    No Known Activations