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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opia
    -0.08
    _imm
    -0.07
    ACT
    -0.07
    نين
    -0.07
    -des
    -0.07
    _fast
    -0.07
    圈
    -0.06
     comics
    -0.06
    Care
    -0.06
    길
    -0.06
    POSITIVE LOGITS
     head
    0.10
    头
    0.08
    勋章
    0.08
    ?p
    0.07
     Deus
    0.07
    MetaData
    0.07
     theories
    0.07
     hypothesis
    0.07
     Hyundai
    0.07
    head
    0.07
    Act Density 0.057%

    No Known Activations