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

    Neuronpedia

    INDEX
    Explanations

    code arguments and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IRCONIUM
    0.48
     convexe
    0.48
     lysed
    0.47
     грошы
    0.46
    Methylsulfanyl
    0.45
    überkü
    0.45
    崤
    0.45
    莹
    0.45
     tumeurs
    0.44
     tumeur
    0.44
    POSITIVE LOGITS
    max
    0.55
     max
    0.54
    disable
    0.52
    force
    0.51
     verbose
    0.51
     allow
    0.50
    allow
    0.49
     use
    0.49
     timeout
    0.46
     min
    0.46
    Act Density 0.046%

    No Known Activations