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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zn
    -0.07
     rời
    -0.07
     hizmet
    -0.07
     Cynthia
    -0.07
     δια
    -0.06
     '['
    -0.06
    зь
    -0.06
     screenshots
    -0.06
     }}>{
    -0.06
    .setContent
    -0.06
    POSITIVE LOGITS
     Possible
    0.06
     assistants
    0.06
    101
    0.06
    –
    0.06
     Opportunity
    0.06
     NGO
    0.06
     handling
    0.06
     FG
    0.05
    Core
    0.05
    -val
    0.05
    Act Density 0.009%

    No Known Activations