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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inter
    0.71
     concession
    0.68
     haunted
    0.67
     scar
    0.66
     scarred
    0.66
     consensus
    0.64
     feud
    0.64
     kon
    0.64
     unattainable
    0.63
     lymphatic
    0.62
    POSITIVE LOGITS
    等
    0.84
     ा
    0.80
    など
    0.77
    ฯ
    0.76
    などを
    0.75
    などの
    0.74
     وغیرہ
    0.74
    小于
    0.73
    等的
    0.72
     등의
    0.70
    Act Density 1.078%

    No Known Activations