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

    Neuronpedia

    INDEX
    Explanations

    Quotations and conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    runs
    -0.07
     Parameters
    -0.07
    -key
    -0.07
    -hand
    -0.06
     Humanity
    -0.06
     $("#"
    -0.06
     manifested
    -0.06
    ίας
    -0.06
     Interaction
    -0.06
     Αγ
    -0.06
    POSITIVE LOGITS
    ↑
    0.07
    霍
    0.06
     jedná
    0.06
    ์ก
    0.06
    SP
    0.06
    .detect
    0.06
     во
    0.06
    .bunifu
    0.05
     bitir
    0.05
    checkpoint
    0.05
    Act Density 0.017%

    No Known Activations