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

    Neuronpedia

    INDEX
    Explanations

    unlike

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AB
    -0.07
     FStar
    -0.07
    站
    -0.06
    /video
    -0.06
    War
    -0.06
    States
    -0.06
    <Data
    -0.06
    656
    -0.06
     �
    -0.06
    μφ
    -0.06
    POSITIVE LOGITS
     depos
    0.07
     регі
    0.06
     Nazis
    0.06
     Depends
    0.06
    .position
    0.06
    igrations
    0.06
    вания
    0.06
    =["
    0.06
    attle
    0.06
     bitch
    0.06
    Act Density 0.162%

    No Known Activations