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

    Neuronpedia

    INDEX
    Explanations

    As a I want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あくまで
    0.57
     android
    0.56
     തന്നെ
    0.54
     kerala
    0.54
     dialog
    0.53
     metaverse
    0.52
     deno
    0.52
     invariable
    0.52
     vetor
    0.51
     dosen
    0.51
    POSITIVE LOGITS
    Brien
    0.62
    르면
    0.60
    arton
    0.57
     Jameson
    0.57
     Thursday
    0.57
     Becky
    0.57
    ackle
    0.56
     Hospice
    0.55
    Jdbc
    0.55
     Wednesday
    0.55
    Act Density 0.002%

    No Known Activations