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

    Neuronpedia

    INDEX
    Explanations

    Femdom, TPE, roleplay scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Valve
    0.38
     گرفتن
    0.38
     formation
    0.37
    Oxford
    0.37
     pinning
    0.37
     ruby
    0.37
     diamonds
    0.36
     infr
    0.36
     expedient
    0.36
    お願いします
    0.35
    POSITIVE LOGITS
    унд
    0.38
     Relationships
    0.38
    рама
    0.38
    芓
    0.37
     Jealous
    0.36
    ኪ
    0.36
    awasan
    0.35
    亞洲
    0.35
     Relationship
    0.35
    bandSize
    0.35
    Act Density 0.000%

    No Known Activations