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

    Neuronpedia

    INDEX
    Explanations

    magnetic field measurements

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    character
    -0.07
    idl
    -0.07
     unequiv
    -0.07
    rect
    -0.07
    设施
    -0.07
    .models
    -0.07
     streets
    -0.07
    �
    -0.07
    рак
    -0.07
    left
    -0.07
    POSITIVE LOGITS
     torso
    0.09
     implementation
    0.07
     בנוסף
    0.07
    岣
    0.07
     pct
    0.07
    硍
    0.07
    (use
    0.07
    _travel
    0.07
     parsed
    0.07
     לז
    0.07
    Act Density 0.219%

    No Known Activations