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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mou
    -0.07
     dull
    -0.07
    moved
    -0.07
     chu
    -0.07
     straps
    -0.06
     bold
    -0.06
    _summary
    -0.06
    alis
    -0.06
     clipboard
    -0.06
     stumbled
    -0.06
    POSITIVE LOGITS
     firepower
    0.07
    binding
    0.06
     eman
    0.06
    .native
    0.06
    τικές
    0.06
    aje
    0.06
     reference
    0.06
    ormsg
    0.06
    ))->
    0.06
    _REFERER
    0.06
    Act Density 0.162%

    No Known Activations