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

    Neuronpedia

    INDEX
    Explanations

    ang/the followed by noun/possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuttavia
    0.70
     Cependant
    0.63
    primarily
    0.63
    axis
    0.62
     تاہم
    0.61
     natomiast
    0.60
     ang
    0.60
     преимущественно
    0.60
    neum
    0.60
    および
    0.60
    POSITIVE LOGITS
     realization
    0.65
     betrayal
    0.65
     sacrificio
    0.64
     damage
    0.61
     usefulness
    0.61
     saya
    0.61
     initiation
    0.60
     acceptance
    0.60
     commitment
    0.60
     closeness
    0.59
    Act Density 0.001%

    No Known Activations