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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xygen
    -0.08
    如此
    -0.08
     Vince
    -0.07
    Uno
    -0.07
    Bruce
    -0.07
    Contents
    -0.07
    	dialog
    -0.07
     farmers
    -0.07
     loudly
    -0.07
    lx
    -0.07
    POSITIVE LOGITS
     Through
    0.08
     ear
    0.07
     wrześ
    0.07
    꺅
    0.06
    큇
    0.06
    .RemoveEmptyEntries
    0.06
    -song
    0.06
     וח
    0.06
    _listen
    0.06
    ෆ
    0.06
    Act Density 0.047%

    No Known Activations