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

    Neuronpedia

    INDEX
    Explanations

    families

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WR
    -0.06
     ordained
    -0.06
     refere
    -0.06
    ěž
    -0.06
    &&
    -0.06
    .xr
    -0.06
     telecommunications
    -0.06
     deltas
    -0.05
     &&
    -0.05
     drastically
    -0.05
    POSITIVE LOGITS
    OTS
    0.07
    ٔ
    0.07
    ocurrency
    0.07
    深圳
    0.07
    寶
    0.07
     unpopular
    0.07
     probabilities
    0.06
    είτε
    0.06
    보증금
    0.06
     PKK
    0.06
    Act Density 0.000%

    No Known Activations