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

    Neuronpedia

    INDEX
    Explanations

    start coroutine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ớ
    0.42
    COLOG
    0.39
     karenge
    0.38
    koliko
    0.38
    icture
    0.37
    jecture
    0.37
     হিন্দুদের
    0.37
    angulo
    0.36
    ศ
    0.36
    minas
    0.35
    POSITIVE LOGITS
    nameof
    0.48
     "~/
    0.47
     GetData
    0.47
     "_
    0.44
     nameof
    0.43
     mak
    0.43
    "_
    0.42
    ~/
    0.41
     named
    0.40
     Kong
    0.40
    Act Density 0.000%

    No Known Activations