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

    Neuronpedia

    INDEX
    Explanations

    hedging language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     existe
    -0.07
    -0.07
    -0.07
    -0.07
     asymmetric
    -0.07
    -0.07
    -0.07
    -0.07
    Oracle
    -0.07
    POSITIVE LOGITS
     Worksheet
    0.06
    놓
    0.06
    (per
    0.06
    peer
    0.06
     nationally
    0.05
     отв
    0.05
     Poly
    0.05
    sik
    0.05
     Pont
    0.05
     повед
    0.05
    Act Density 0.012%

    No Known Activations