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

    Neuronpedia

    INDEX
    Explanations

    User or customer related content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outspoken
    -0.07
    Phys
    -0.07
    立
    -0.06
     王
    -0.06
    _dropdown
    -0.06
    ucs
    -0.06
    -oriented
    -0.06
     політи
    -0.06
     felse
    -0.06
     inconsistency
    -0.06
    POSITIVE LOGITS
    lld
    0.06
    ,
    0.06
     परम
    0.06
     disreg
    0.06
     расс
    0.06
    .pending
    0.06
    ylon
    0.05
     GAL
    0.05
    ても
    0.05
    gba
    0.05
    Act Density 0.100%

    No Known Activations