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

    Neuronpedia

    INDEX
    Explanations

    directed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mundo
    -0.07
     textbooks
    -0.06
     liquid
    -0.06
     ALOG
    -0.06
     journals
    -0.06
     apt
    -0.06
     breathing
    -0.06
     덤프
    -0.06
     thematic
    -0.06
    IfExists
    -0.06
    POSITIVE LOGITS
    権
    0.07
    ушка
    0.06
    .Initial
    0.06
    -BEGIN
    0.06
    Grace
    0.06
     ruin
    0.06
    .storage
    0.06
     disadvantaged
    0.06
     unstoppable
    0.06
    .Dialog
    0.06
    Act Density 0.002%

    No Known Activations