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

    Neuronpedia

    INDEX
    Explanations

    requests for additional data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blogs
    0.86
     blogging
    0.80
     בד
    0.80
    ీల
    0.75
    blogs
    0.73
     Blogs
    0.72
     Blog
    0.72
     anál
    0.70
     análise
    0.69
     blogger
    0.69
    POSITIVE LOGITS
     request
    0.68
     homeostasis
    0.66
    resources
    0.64
     discriminated
    0.63
     emergencies
    0.63
     escalate
    0.62
     closure
    0.61
    구성
    0.60
     requesting
    0.59
     requests
    0.59
    Act Density 0.757%

    No Known Activations