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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sr
    -0.07
     Crash
    -0.07
     Durham
    -0.06
     stormed
    -0.06
     myfile
    -0.06
    ilated
    -0.06
    Heroes
    -0.06
     calorie
    -0.06
     killings
    -0.06
     ΑΓ
    -0.06
    POSITIVE LOGITS
     EPA
    0.07
     FindObjectOfType
    0.07
     더욱
    0.07
     뿐
    0.06
     tutor
    0.06
     qualidade
    0.06
    設
    0.06
    uman
    0.06
    ﾆﾆ
    0.06
    ，可以
    0.06
    Act Density 0.001%

    No Known Activations