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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ='#
    -0.06
    lamp
    -0.06
    965
    -0.06
     Steph
    -0.06
    Then
    -0.06
     Bath
    -0.06
     anytime
    -0.06
    .SC
    -0.06
    겠
    -0.06
     Zah
    -0.06
    POSITIVE LOGITS
    (code
    0.07
     adverts
    0.07
     um
    0.07
     créd
    0.07
    (shift
    0.07
    ική
    0.06
     op
    0.06
    �다
    0.06
    _property
    0.06
     lawmakers
    0.06
    Act Density 0.003%

    No Known Activations