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

    Neuronpedia

    INDEX
    Explanations

    able

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rider
    -0.07
     epith
    -0.07
    .WinControls
    -0.06
    ve
    -0.06
     Fa
    -0.06
     cooling
    -0.06
    =id
    -0.06
    .Active
    -0.06
     stark
    -0.06
    πι
    -0.06
    POSITIVE LOGITS
     beg
    0.09
     Beg
    0.09
     생각
    0.07
    Sharing
    0.06
     الخاص
    0.06
     semble
    0.06
     самых
    0.06
    ANCE
    0.06
     вони
    0.06
     Humans
    0.06
    Act Density 0.001%

    No Known Activations