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

    Neuronpedia

    INDEX
    Explanations

    "+"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dul
    -0.08
    .vector
    -0.07
    .coordinate
    -0.07
     educational
    -0.07
    HANDLE
    -0.07
    Sus
    -0.07
    伞
    -0.07
     cookie
    -0.07
     FileAccess
    -0.07
    restore
    -0.06
    POSITIVE LOGITS
     later
    0.07
     emo
    0.07
     różnych
    0.07
    :function
    0.07
    igraphy
    0.06
     Hobby
    0.06
    emics
    0.06
     ign
    0.06
    сет
    0.06
    prove
    0.06
    Act Density 0.006%

    No Known Activations