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

    Neuronpedia

    INDEX
    Explanations

    encoder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ा.↵
    -0.07
    ..."↵
    -0.06
    ную
    -0.06
    precation
    -0.06
    .dylib
    -0.06
    xcb
    -0.06
    WHERE
    -0.06
    .StringVar
    -0.06
    ())))↵
    -0.06
    来自
    -0.06
    POSITIVE LOGITS
     pioneer
    0.07
     kı
    0.07
    мот
    0.07
     alarmed
    0.06
     stressful
    0.06
     віднов
    0.06
     urge
    0.06
     reassuring
    0.06
     preventing
    0.06
     stresses
    0.06
    Act Density 0.008%

    No Known Activations