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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pulp
    -0.07
     engineers
    -0.07
    NASA
    -0.07
    新的
    -0.06
     Regel
    -0.06
     preempt
    -0.06
     executions
    -0.06
     pref
    -0.06
     ry
    -0.06
     зберіг
    -0.06
    POSITIVE LOGITS
    疾
    0.07
     Між
    0.06
    忆
    0.06
    quipe
    0.06
    одерж
    0.06
     PMC
    0.06
     خ
    0.06
    /write
    0.05
    
    0.05
     dlg
    0.05
    Act Density 0.526%

    No Known Activations