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

    Neuronpedia

    INDEX
    Explanations

    composting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ღ
    -0.07
    pdf
    -0.07
     орг
    -0.07
    一枚
    -0.07
     Rex
    -0.07
     hull
    -0.07
    .AR
    -0.07
     Break
    -0.07
     pers
    -0.06
    .startActivity
    -0.06
    POSITIVE LOGITS
    BUFFER
    0.07
    �
    0.07
    تاريخ
    0.07
    expo
    0.07
    wró
    0.07
    猢
    0.06
     trov
    0.06
    瓢
    0.06
    pired
    0.06
    老
    0.06
    Act Density 0.026%

    No Known Activations