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

    Neuronpedia

    INDEX
    Explanations

    yes/no prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conocer
    -0.08
    Come
    -0.07
    ita
    -0.07
    uvre
    -0.07
    asured
    -0.07
     설명
    -0.07
    vue
    -0.06
    왔다
    -0.06
     definitive
    -0.06
    应对
    -0.06
    POSITIVE LOGITS
    Nullable
    0.08
     prophets
    0.07
    ⊣
    0.07
    쁨
    0.07
     Clients
    0.07
     Günc
    0.06
     Rigidbody
    0.06
     JOB
    0.06
    ]->
    0.06
    ᶱ
    0.06
    Act Density 0.006%

    No Known Activations