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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     philosoph
    -0.06
     parl
    -0.06
    	settings
    -0.06
     '\\
    -0.06
     therein
    -0.06
     Broad
    -0.06
     zeal
    -0.06
    stre
    -0.06
    节点
    -0.06
    189
    -0.06
    POSITIVE LOGITS
     أمر
    0.09
    MB
    0.08
    MI
    0.08
    ━━
    0.08
    Mt
    0.08
    MD
    0.08
    MMC
    0.08
    mil
    0.07
    MPI
    0.07
    CTOR
    0.07
    Act Density 0.028%

    No Known Activations