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

    Neuronpedia

    INDEX
    Explanations

    multi-script, specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     چاہئے
    0.53
    ano
    0.51
    ide
    0.51
    ProxyAgent
    0.50
    erebbe
    0.50
     केल्या
    0.50
     صوب
    0.49
    ৱ
    0.49
    Probe
    0.48
     Dazu
    0.46
    POSITIVE LOGITS
    ف
    0.68
    ם
    0.61
    亿
    0.60
     results
    0.56
     in
    0.55
     kth
    0.54
    ت
    0.52
    سون
    0.52
     been
    0.51
     anterior
    0.51
    Act Density 0.000%

    No Known Activations