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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prized
    -0.07
    host
    -0.07
     inquire
    -0.06
    add
    -0.06
     Glo
    -0.06
    distinct
    -0.06
    atar
    -0.06
    cod
    -0.06
    angers
    -0.06
    ,line
    -0.06
    POSITIVE LOGITS
     spontaneously
    0.07
    .W
    0.07
     ActionController
    0.07
     látky
    0.06
    141
    0.06
    >'
↵
    0.06
     '//
    0.06
     Milky
    0.06
     ΔE
    0.06
    /****************
    0.06
    Act Density 0.000%

    No Known Activations