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

    Neuronpedia

    INDEX
    Explanations

    looking for information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     useful
    -0.07
    配电
    -0.07
     explore
    -0.07
    _sa
    -0.07
     embodied
    -0.07
     Xia
    -0.07
    .write
    -0.07
    ForKey
    -0.07
    .can
    -0.07
     Continuous
    -0.06
    POSITIVE LOGITS
    itably
    0.07
    outline
    0.07
     fridge
    0.06
    大发
    0.06
    ResultSet
    0.06
    녀
    0.06
    abler
    0.06
    탯
    0.06
     płyn
    0.06
    ildo
    0.06
    Act Density 0.021%

    No Known Activations