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

    Neuronpedia

    INDEX
    Explanations

    Medical/technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſtate
    -1.29
     myſelf
    -1.24
     uſed
    -1.22
     himſelf
    -1.20
    ſelf
    -1.20
     themſelves
    -1.20
     itſelf
    -1.18
     poffible
    -1.18
     ftate
    -1.17
     houſe
    -1.16
    POSITIVE LOGITS
     (
    0.48
     as
    0.42
     
    0.40
    (
    0.39
     also
    0.36
    ↵↵
    0.36
    ↵
    0.35
     no
    0.35
     *
    0.35
    ,
    0.35
    Act Density 0.002%

    No Known Activations