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

    Neuronpedia

    INDEX
    Explanations

    slashes and symbols commonly associated with file paths and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    path separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TestBed
    -0.74
    TestBed
    -0.53
     dieß
    -0.52
    WebVitals
    -0.47
    localctx
    -0.47
    Datuak
    -0.46
    Hentet
    -0.44
    НАЯ
    -0.44
    Kra
    -0.44
    Elena
    -0.43
    POSITIVE LOGITS
    ("/")
    0.60
    ('/')
    0.58
     '/'
    0.52
    ("/");
    0.52
     '/')
    0.51
     '/':
    0.51
     "/"
    0.50
    ('/');
    0.50
     "/")
    0.46
     "/",
    0.45
    Act Density 0.016%

    No Known Activations