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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shedding
    -0.06
    userinfo
    -0.06
     riding
    -0.06
     decades
    -0.06
    .Im
    -0.06
    	ad
    -0.06
    �
    -0.06
    ポ
    -0.06
    ों
    -0.06
    _Success
    -0.06
    POSITIVE LOGITS
    aqu
    0.07
    '),↵↵
    0.06
    _patches
    0.06
    agna
    0.06
    nger
    0.06
    KV
    0.06
    .currentTarget
    0.06
    契
    0.06
    esty
    0.06
    quiv
    0.06
    Act Density 0.001%

    No Known Activations