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

    Neuronpedia

    INDEX
    Explanations

    Audio/hearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =["
    -0.07
     Norte
    -0.06
    .lo
    -0.06
    ेबस
    -0.06
    antor
    -0.06
    elfth
    -0.06
    -sum
    -0.06
    _IS
    -0.06
     letra
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     formatting
    0.06
     wow
    0.06
     Len
    0.06
    แปลง
    0.06
    Massage
    0.06
     overwhelm
    0.06
    moz
    0.06
     reim
    0.06
     milan
    0.06
     admission
    0.06
    Act Density 0.006%

    No Known Activations