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

    Neuronpedia

    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unda
    -0.07
    Interactive
    -0.07
     forestry
    -0.07
     curso
    -0.06
     chuyện
    -0.06
    .ENTER
    -0.06
    _PERSON
    -0.06
    _START
    -0.06
     cautious
    -0.06
    .getItem
    -0.06
    POSITIVE LOGITS
    libs
    0.06
    )?;↵
    0.06
    ятий
    0.06
    urma
    0.06
     bill
    0.06
    ')){↵
    0.06
    hack
    0.06
     wraps
    0.06
    (co
    0.06
    ？”
    0.06
    Act Density 0.007%

    No Known Activations