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

    Neuronpedia

    INDEX
    Explanations

    carry what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.53
     』
    0.50
    』
    0.48
     be
    0.47
    </h5>
    0.43
     graduate
    0.43
     heater
    0.43
    </i>
    0.43
     수도
    0.42
     कोलो
    0.42
    POSITIVE LOGITS
     Фурга
    0.61
     sassy
    0.55
    Tarea
    0.53
    iggio
    0.51
     Гинд
    0.51
    securityMarks
    0.51
    芾
    0.51
     Dessous
    0.50
     Nizam
    0.49
     vucc
    0.48
    Act Density 0.000%

    No Known Activations