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

    Neuronpedia

    INDEX
    Explanations

    ocean

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    爱人
    -0.08
     validity
    -0.07
     Www
    -0.07
     veto
    -0.07
    argins
    -0.07
     receipt
    -0.07
     participate
    -0.07
    朋友们对
    -0.07
     XmlDocument
    -0.07
    >false
    -0.07
    POSITIVE LOGITS
     ocean
    0.09
    ארגון
    0.08
     Ober
    0.07
     кли
    0.07
     incess
    0.06
    掃
    0.06
    arme
    0.06
    큭
    0.06
     Ocean
    0.06
    औ
    0.06
    Act Density 0.005%

    No Known Activations