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

    Neuronpedia

    INDEX
    Explanations

    7 followed by numbers or common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused295>
    0.54
    करण
    0.50
    没有
    0.49
    猕
    0.47
    
    0.47
     बहिष्कार
    0.47
    ‌است
    0.46
    তীর্থ
    0.46
    chec
    0.46
    从业
    0.46
    POSITIVE LOGITS
     REGIUNI
    0.54
     deadly
    0.52
    ول
    0.52
    д
    0.52
     dwarfs
    0.49
    ود
    0.48
    c
    0.47
     Deadly
    0.46
     In
    0.44
     Dwar
    0.42
    Act Density 0.045%

    No Known Activations