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

    Neuronpedia

    INDEX
    Explanations

    his Chinese phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slows
    0.59
     textvariable
    0.52
     highlighted
    0.52
     simulates
    0.51
     стране
    0.50
     collaborates
    0.49
     underlies
    0.46
     ентите
    0.46
     undermines
    0.45
    }((
    0.45
    POSITIVE LOGITS
    Grant
    0.50
    杓
    0.50
    脑
    0.49
    他的
    0.47
    Rate
    0.46
     Mardi
    0.46
    Thanks
    0.45
    Price
    0.45
     Tourism
    0.44
    烜
    0.44
    Act Density 0.001%

    No Known Activations