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

    Neuronpedia

    INDEX
    Explanations

    Objective/Interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.24
     purpoſe
    -1.20
     myſelf
    -1.19
     ſta
    -1.18
     ſche
    -1.12
     itſelf
    -1.12
     houſe
    -1.10
     Chriftian
    -1.06
     uſe
    -1.05
     ſtate
    -1.05
    POSITIVE LOGITS
     of
    0.60
     Gar
    0.57
     
    0.54
     Ter
    0.54
     "
    0.52
     Time
    0.52
     Per
    0.52
     Tom
    0.52
     I
    0.51
     Bar
    0.51
    Act Density 0.426%

    No Known Activations