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

    Neuronpedia

    INDEX
    Explanations

    Describing subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affiliated
    -0.08
    Breaking
    -0.07
    Phi
    -0.07
     Rash
    -0.07
     �
    -0.06
     Ped
    -0.06
    	padding
    -0.06
    描述
    -0.06
     blends
    -0.06
    вание
    -0.06
    POSITIVE LOGITS
    ồi
    0.07
    ooter
    0.06
    pNet
    0.06
    .at
    0.06
    __(↵
    0.06
    llib
    0.06
     Enemies
    0.06
     thăm
    0.06
    ılıç
    0.06
     donc
    0.06
    Act Density 0.015%

    No Known Activations