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

    Neuronpedia

    INDEX
    Explanations

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RMSE
    0.79
     VLAN
    0.76
     Jira
    0.75
     Señor
    0.74
     ორგან
    0.74
     LDAP
    0.73
     Jupyter
    0.73
     regex
    0.72
     Ryanair
    0.72
     obfusc
    0.72
    POSITIVE LOGITS
    -%
    1.25
    /?
    1.17
    /)
    1.12
    ](
    1.09
    article
    1.09
    html
    1.08
    #:
    1.08
    articles
    1.06
    #!
    1.02
    #!/
    1.01
    Act Density 0.425%

    No Known Activations