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

    Neuronpedia

    INDEX
    Explanations

    code snippets and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     webhook
    0.61
      
    0.60
     vant
    0.60
     OpenAI
    0.59
     rigid
    0.58
     platform
    0.58
     output
    0.57
     indirect
    0.56
     input
    0.55
     biomed
    0.55
    POSITIVE LOGITS
    <unused1881>
    0.57
    <unused567>
    0.56
    <unused951>
    0.52
    <unused1670>
    0.52
    პ
    0.52
    <unused988>
    0.52
    <unused1138>
    0.51
    ᱾
    0.49
    <unused2041>
    0.49
    <unused2102>
    0.49
    Act Density 0.096%

    No Known Activations