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

    Neuronpedia

    INDEX
    Explanations

    competitors or demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positions
    0.38
     있다면
    0.38
     позиции
    0.37
    ការព
    0.37
    මා
    0.36
     armchair
    0.36
     용
    0.35
    স্তাফিজ
    0.35
     closed
    0.35
     council
    0.35
    POSITIVE LOGITS
    又不
    0.45
    弔
    0.40
    compet
    0.36
     ટે
    0.36
    hence
    0.35
     checkout
    0.35
    Â
    0.35
     tempos
    0.35
     Dynamics
    0.35
     compet
    0.34
    Act Density 0.000%

    No Known Activations