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

    Neuronpedia

    INDEX
    Explanations

    math problems (worded)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOB
    -0.08
    TECTION
    -0.07
    .TEXTURE
    -0.07
     recurrence
    -0.07
     TPP
    -0.06
     Cz
    -0.06
    941
    -0.06
     VAL
    -0.06
     KY
    -0.06
    ของผ
    -0.06
    POSITIVE LOGITS
     flakes
    0.06
     nop
    0.06
     empt
    0.06
    划
    0.06
     prompted
    0.06
    _ut
    0.06
    şam
    0.06
     공부
    0.06
     Revised
    0.06
     ώ
    0.06
    Act Density 0.015%

    No Known Activations