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

    Neuronpedia

    INDEX
    Explanations

    world/earth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matchmaking
    -0.07
    Specifies
    -0.07
    bellion
    -0.06
    rors
    -0.06
     सर
    -0.06
    respons
    -0.06
     IKE
    -0.06
    zeros
    -0.06
     hers
    -0.06
     kys
    -0.06
    POSITIVE LOGITS
    DidEnter
    0.07
    ![
    0.07
    Monitoring
    0.07
    }
↵
↵
    0.07
    .Refresh
    0.07
     захід
    0.06
     shaping
    0.06
    iming
    0.06
    ToList
    0.06
    .Save
    0.06
    Act Density 0.021%

    No Known Activations