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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aste
    -0.07
    _VLAN
    -0.06
     Buen
    -0.06
    !";
↵
    -0.06
    libraries
    -0.06
     Surre
    -0.06
    Ik
    -0.06
    resource
    -0.06
    Wonder
    -0.06
     Variation
    -0.06
    POSITIVE LOGITS
     privile
    0.06
    �
    0.06
    ี,
    0.06
    tot
    0.06
     errorCallback
    0.06
     solutions
    0.06
    ーバ
    0.06
     rost
    0.06
     deflate
    0.05
    illa
    0.05
    Act Density 0.033%

    No Known Activations