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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arm
    -0.07
     displayName
    -0.07
    كرة
    -0.07
    ації
    -0.07
    ロン
    -0.07
    Definition
    -0.06
     glyc
    -0.06
    ฟ
    -0.06
    click
    -0.06
     unthinkable
    -0.06
    POSITIVE LOGITS
     ≈
    0.07
    �
    0.07
     CID
    0.06
    .df
    0.06
     pct
    0.06
    CED
    0.06
     ventures
    0.06
     IIC
    0.06
    legacy
    0.06
     seminars
    0.06
    Act Density 0.239%

    No Known Activations