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

    Neuronpedia

    INDEX
    Explanations

    naming companies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wanneer
    -0.09
     uitge
    -0.09
     onderste
    -0.08
     വിശദ
    -0.08
    יאור
    -0.08
    Beschreibung
    -0.08
     toen
    -0.08
     overlapping
    -0.08
     bookmarked
    -0.08
    説明
    -0.08
    POSITIVE LOGITS
     Secrets
    0.09
     немесе
    0.08
     বা
    0.08
     அல்லது
    0.08
    Suffix
    0.08
    -inspired
    0.08
     ಅಥವಾ
    0.08
    omething
    0.08
     destiny
    0.07
     किंवा
    0.07
    Act Density 0.022%

    No Known Activations