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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桑
    -0.06
    Ka
    -0.06
     Ke
    -0.06
    _TIMES
    -0.06
    urile
    -0.06
    気持ち
    -0.06
    _na
    -0.06
    CJK
    -0.06
    La
    -0.06
     tex
    -0.06
    POSITIVE LOGITS
    �
    0.07
    roup
    0.07
    	location
    0.07
     weld
    0.07
    Methods
    0.06
     Rosa
    0.06
    (button
    0.06
    msgid
    0.06
    amam
    0.06
     climbing
    0.06
    Act Density 0.000%

    No Known Activations