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

    Neuronpedia

    INDEX
    Explanations

    Math probability questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleasant
    -0.07
     Antarctica
    -0.07
    فته
    -0.07
     devout
    -0.07
    Stories
    -0.07
     pioneer
    -0.06
     Nested
    -0.06
     switched
    -0.06
    -hand
    -0.06
     interview
    -0.06
    POSITIVE LOGITS
     развити
    0.06
    ею
    0.06
    üns
    0.06
    velle
    0.06
    оруж
    0.06
    .python
    0.05
    olla
    0.05
    ันด
    0.05
    UpEdit
    0.05
    �
    0.05
    Act Density 0.038%

    No Known Activations