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

    Neuronpedia

    INDEX
    Explanations

    hopefully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     решения
    -0.07
     SAS
    -0.07
     Edinburgh
    -0.07
     MADE
    -0.06
     noci
    -0.06
    IBLE
    -0.06
    agr
    -0.06
    Slides
    -0.06
     wedge
    -0.06
     kann
    -0.06
    POSITIVE LOGITS
    hopefully
    0.09
     hopefully
    0.09
     Hopefully
    0.08
    Hopefully
    0.08
     mouseX
    0.07
    ồi
    0.07
     combos
    0.07
     convoy
    0.07
     bezpeč
    0.06
     Come
    0.06
    Act Density 0.006%

    No Known Activations