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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reff
    -0.26
    borrow
    -0.25
    å®ĹæķĻ
    -0.24
    stin
    -0.24
    argas
    -0.23
    åıĮåıĮ
    -0.23
     gamm
    -0.23
    -validation
    -0.23
    cline
    -0.23
     stere
    -0.23
    POSITIVE LOGITS
    ç¬ĥ
    0.30
    ocity
    0.29
    èĦ±
    0.27
    [âĢ¦
    0.25
     screen
    0.25
    æľĢç¾İçļĦ
    0.25
     dist
    0.25
    urv
    0.25
    å¹ķ
    0.24
    igo
    0.24
    Act Density 1.457%

    No Known Activations