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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oscillators
    0.44
    ̀u
    0.39
     manuscripts
    0.39
     illustrations
    0.38
     hides
    0.38
     print
    0.38
    敤
    0.38
     lied
    0.37
     elasticity
    0.37
     filesize
    0.37
    POSITIVE LOGITS
    hadow
    0.40
    Titles
    0.38
    írez
    0.38
    泛
    0.37
    제목
    0.37
    춥
    0.36
     surpr
    0.36
    sums
    0.35
     JSONObject
    0.35
     rendez
    0.34
    Act Density 0.000%

    No Known Activations