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

    Neuronpedia

    INDEX
    Explanations

    Black

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чист
    -0.07
     также
    -0.07
     material
    -0.07
    查
    -0.07
     Control
    -0.07
     poslední
    -0.07
     thirst
    -0.06
    ิจารณ
    -0.06
    Town
    -0.06
     setLocation
    -0.06
    POSITIVE LOGITS
    _FRONT
    0.07
    -bodied
    0.07
    _MAKE
    0.07
    Inv
    0.06
     århus
    0.06
    bones
    0.06
    !
↵
    0.06
    ArrayType
    0.06
    ]*
    0.06
    MESSAGE
    0.06
    Act Density 0.116%

    No Known Activations