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

    Neuronpedia

    INDEX
    Explanations

    ind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сосуд
    -0.07
    should
    -0.06
     Hoover
    -0.06
     Kimber
    -0.06
     कव
    -0.06
    expected
    -0.06
     Hayward
    -0.06
    隔
    -0.06
     Mathf
    -0.06
     thinner
    -0.06
    POSITIVE LOGITS
     popul
    0.07
    AL
    0.07
     madrid
    0.06
    片
    0.06
    보다
    0.06
    backs
    0.06
     한
    0.06
     TextStyle
    0.06
    ’:
    0.06
    al
    0.06
    Act Density 0.001%

    No Known Activations