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

    Neuronpedia

    INDEX
    Explanations

    actic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ραν
    -0.08
    jualan
    -0.07
     confirmed
    -0.07
    (validation
    -0.06
    enery
    -0.06
    िजन
    -0.06
     stride
    -0.06
     Perkins
    -0.06
     온라인
    -0.06
    ламент
    -0.06
    POSITIVE LOGITS
     photoshop
    0.07
    embourg
    0.06
     Beverly
    0.06
     researchers
    0.06
     happily
    0.06
    $/,
    0.06
    -cart
    0.06
    ★★
    0.06
    とか
    0.06
    )((
    0.06
    Act Density 0.001%

    No Known Activations