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

    Neuronpedia

    INDEX
    Explanations

    approximate costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     লিল
    0.44
     Consul
    0.42
     ない
    0.41
    reux
    0.41
     consul
    0.39
    无
    0.39
     interesados
    0.38
    bolinks
    0.38
    uyendo
    0.37
    因素
    0.37
    POSITIVE LOGITS
     conséquence
    0.41
     прив
    0.38
     accumulation
    0.37
     चली
    0.36
     strange
    0.36
    CharSequence
    0.36
    geführt
    0.35
    Escape
    0.35
     حسن
    0.35
    леп
    0.35
    Act Density 0.001%

    No Known Activations