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

    Neuronpedia

    INDEX
    Explanations

    reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     saba
    -0.08
     ters
    -0.07
    Asset
    -0.07
    Univers
    -0.07
     indis
    -0.07
     SBA
    -0.07
    .mar
    -0.07
     mub
    -0.07
     martial
    -0.07
    -0.07
    POSITIVE LOGITS
    能力
    0.14
     능
    0.12
     திற
    0.10
     abilities
    0.09
     способности
    0.09
     ability
    0.09
     capability
    0.09
     capabilities
    0.08
     capacidad
    0.08
     क्षमता
    0.08
    Act Density 0.006%
    No Known Activations