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

    Neuronpedia

    INDEX
    Explanations

    transf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vyrá
    -0.07
    _OPCODE
    -0.07
     aktivit
    -0.06
     abras
    -0.06
     Бер
    -0.06
    igraphy
    -0.06
     Uk
    -0.06
    _blocking
    -0.06
     lokal
    -0.06
    _arc
    -0.06
    POSITIVE LOGITS
     transf
    0.12
     transl
    0.08
    /d
    0.07
     Account
    0.07
     adm
    0.07
     interact
    0.07
    	transform
    0.06
     insight
    0.06
    Self
    0.06
    。↵↵↵↵
    0.06
    Act Density 0.002%

    No Known Activations