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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frags
    -0.07
     Teddy
    -0.07
     chaining
    -0.06
     generics
    -0.06
    ibrated
    -0.06
     Morr
    -0.06
     itens
    -0.06
    .validator
    -0.06
    \Factory
    -0.06
     threatening
    -0.06
    POSITIVE LOGITS
    "context
    0.13
     dahi
    0.08
     CX
    0.07
     homosexuality
    0.07
     pron
    0.06
    ительно
    0.06
    .mybatis
    0.06
     kişinin
    0.06
     projectile
    0.06
     Rodney
    0.06
    Act Density 0.001%

    No Known Activations