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

    Neuronpedia

    INDEX
    Explanations

    filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ideshow
    -0.07
    תזונה
    -0.07
    ependency
    -0.07
    connect
    -0.07
    endedor
    -0.07
    etration
    -0.07
     Identification
    -0.07
     universally
    -0.06
     otherwise
    -0.06
     watched
    -0.06
    POSITIVE LOGITS
     ]↵
    0.08
     =============================================================================↵
    0.07
     brute
    0.07
    ']]↵
    0.07
    สล
    0.07
    .'"↵↵
    0.07
    *);↵
    0.07
    ']↵
    0.07
    ")));↵
    0.07
    ')])↵
    0.07
    Act Density 0.051%

    No Known Activations