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

    Neuronpedia

    INDEX
    Explanations

    open chatbot or LLM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
     in
    0.46
     on
    0.38
     I
    0.38
    ,
    0.38
     is
    0.37
     de
    0.37
    -
    0.37
     In
    0.36
     of
    0.36
    POSITIVE LOGITS
     коронави
    0.44
    springboot
    0.42
    assignmentItems
    0.41
     букмекерлер
    0.40
    SpringBoot
    0.40
     божомолдору
    0.39
     кеңсесинде
    0.39
     způ
    0.39
     fonbet
    0.38
    myapplication
    0.38
    Act Density 0.000%

    No Known Activations