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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Judge
    -0.07
     swell
    -0.06
    ��作
    -0.06
     phased
    -0.06
     stern
    -0.06
    ActionTypes
    -0.06
    热心
    -0.06
     así
    -0.06
    쉘
    -0.06
    利
    -0.06
    POSITIVE LOGITS
    衰退
    0.07
     vüc
    0.07
     hormone
    0.07
     Protocol
    0.07
    	SC
    0.07
    ']="
    0.06
     dort
    0.06
    _IDENTIFIER
    0.06
     reacted
    0.06
    -Ray
    0.06
    Act Density 0.022%

    No Known Activations