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

    Neuronpedia

    INDEX
    Explanations

    alternatives, soul, fresh, job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoodies
    0.51
     entreprises
    0.49
    middleware
    0.49
     adverts
    0.49
    ફેદ
    0.48
    মুখি
    0.48
     layoffs
    0.47
     barring
    0.47
     everytime
    0.47
     doorways
    0.46
    POSITIVE LOGITS
    ”
    0.53
    烺
    0.51
    }
    0.49
    Addition
    0.47
    Ag
    0.47
    的一
    0.47
    去
    0.46
    太阳
    0.46
    Act
    0.44
    Mary
    0.44
    Act Density 0.004%

    No Known Activations