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

    Neuronpedia

    INDEX
    Explanations

    code or math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     玩
    -0.07
    afone
    -0.07
    ]->
    -0.06
     муз
    -0.06
     bare
    -0.06
    enguins
    -0.06
     Chapel
    -0.06
    πτυ
    -0.06
     marin
    -0.06
     fingerprints
    -0.06
    POSITIVE LOGITS
    Contacts
    0.07
     enorme
    0.07
    706
    0.07
     rejoice
    0.06
     هم
    0.06
    ƒ
    0.06
     harms
    0.06
    戦
    0.06
     unbelie
    0.06
     Amnesty
    0.06
    Act Density 0.007%

    No Known Activations