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

    Neuronpedia

    INDEX
    Explanations

    number sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cinder
    -0.07
    てくる
    -0.07
     ngôi
    -0.06
    ことが
    -0.06
     transmissions
    -0.06
    _Call
    -0.06
     stair
    -0.06
     *)&
    -0.06
    iosity
    -0.06
     Corvette
    -0.06
    POSITIVE LOGITS
    PRECATED
    0.08
    应当
    0.07
    详解
    0.07
    璆
    0.06
    />↵
    0.06
    	sl
    0.06
     Include
    0.06
     DP
    0.06
    uffer
    0.06
    なら
    0.06
    Act Density 0.020%

    No Known Activations