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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iVar
    -0.07
     Fol
    -0.06
    暫
    -0.06
     opposition
    -0.06
    憙
    -0.06
     stellen
    -0.06
    捣
    -0.06
    -Nov
    -0.06
    oscopic
    -0.06
     Ton
    -0.06
    POSITIVE LOGITS
    شركات
    0.07
    еча
    0.07
    ANTED
    0.07
     DESC
    0.07
    cea
    0.07
    reachable
    0.07
     APPLICATION
    0.07
    computed
    0.07
    被困
    0.07
     Rew
    0.07
    Act Density 0.060%

    No Known Activations