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

    Neuronpedia

    INDEX
    Explanations

    code references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _circle
    -0.07
    .FieldName
    -0.06
    Ni
    -0.06
    	RE
    -0.06
     contr
    -0.06
     prisoner
    -0.06
     klient
    -0.06
    질
    -0.06
     keys
    -0.06
    geom
    -0.06
    POSITIVE LOGITS
    确认
    0.07
     SDK
    0.07
    regions
    0.07
     hindsight
    0.06
     мені
    0.06
    】
    0.06
     raining
    0.06
     overse
    0.06
     allergies
    0.06
    ivist
    0.06
    Act Density 0.003%

    No Known Activations