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

    Neuronpedia

    INDEX
    Explanations

    how are you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.49
       
    0.46
        
    0.46
     threatening
    0.45
    T
    0.42
    </b>
    0.42
    െ
    0.42
    Threat
    0.41
     hospital
    0.41
     Jose
    0.41
    POSITIVE LOGITS
    áticamente
    0.59
    <unused519>
    0.56
     रिप्रोड
    0.55
    🈺
    0.55
    🕤
    0.54
    AGRAM
    0.53
    𒇻
    0.53
    ÉE
    0.52
     spineItem
    0.52
    🕣
    0.52
    Act Density 0.001%

    No Known Activations