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

    Neuronpedia

    INDEX
    Explanations

    software documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     charity
    -0.11
    网友
    -0.10
     vero
    -0.10
     tweet
    -0.10
     rampant
    -0.10
    /social
    -0.10
     societ
    -0.09
     vibe
    -0.09
     vibes
    -0.09
     Nietzsche
    -0.09
    POSITIVE LOGITS
     troubleshooting
    0.10
     VMware
    0.09
     troubleshoot
    0.09
     Jira
    0.09
    Prere
    0.08
     beachten
    0.08
    .Once
    0.08
    LDAP
    0.08
    xref
    0.08
     verwenden
    0.08
    Act Density 0.085%

    No Known Activations