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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仅
    -0.07
     Hell
    -0.07
     housed
    -0.07
     Harvard
    -0.07
     oldest
    -0.06
     Cedar
    -0.06
     yet
    -0.06
     afterEach
    -0.06
    616
    -0.06
    _least
    -0.06
    POSITIVE LOGITS
    InstanceState
    0.07
     TOO
    0.07
    )NULL
    0.06
     yo
    0.06
    amente
    0.06
    UserCode
    0.06
    CHO
    0.06
    メント
    0.06
    .social
    0.06
    …"↵↵
    0.06
    Act Density 0.050%

    No Known Activations