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

    Neuronpedia

    INDEX
    Explanations

    games/seasons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responsible
    -0.07
    _);↵↵
    -0.06
     поч
    -0.06
     transporter
    -0.06
    anford
    -0.06
     rugged
    -0.05
     resonate
    -0.05
    .Animation
    -0.05
     GridBagConstraints
    -0.05
     loc
    -0.05
    POSITIVE LOGITS
    _shared
    0.08
    yes
    0.07
    _bw
    0.07
    ANS
    0.07
     жид
    0.06
    _assignment
    0.06
     Dtype
    0.06
     अप
    0.06
    อะ
    0.06
     MIS
    0.06
    Act Density 0.020%

    No Known Activations