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

    Neuronpedia

    INDEX
    Explanations

    built

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iked
    -0.07
     stringent
    -0.06
    Chunks
    -0.06
    -city
    -0.06
    aussian
    -0.06
     commenting
    -0.06
    ategic
    -0.06
    Ｒ
    -0.06
    ถาน
    -0.06
    AC
    -0.06
    POSITIVE LOGITS
    mot
    0.06
    _f
    0.06
     Plaint
    0.06
    -have
    0.06
    _PID
    0.06
     leo
    0.06
     тим
    0.06
    �
    0.06
     interrupts
    0.06
    _APPEND
    0.06
    Act Density 0.004%

    No Known Activations