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

    Neuronpedia

    INDEX
    Explanations

    differentiate or make choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    分け
    0.41
    洋
    0.40
    Para
    0.39
    Dengan
    0.38
     विद
    0.37
    ActionEvent
    0.37
    0.36
     Dengan
    0.35
    height
    0.34
    以上
    0.34
    POSITIVE LOGITS
     pollin
    0.47
     apoyar
    0.42
     Silverstone
    0.41
     rejoined
    0.41
     Tej
    0.40
     Brilliant
    0.40
     moonlight
    0.40
     Moonlight
    0.39
    क्सन
    0.39
    AudioFocus
    0.39
    Act Density 0.005%

    No Known Activations