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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handle
    -0.07
     Happy
    -0.07
    gang
    -0.07
    очно
    -0.06
    ữa
    -0.06
     vibrant
    -0.06
     Dash
    -0.06
     reimbursement
    -0.06
     wang
    -0.06
    schema
    -0.06
    POSITIVE LOGITS
     oath
    0.07
    ConfigureAwait
    0.07
    ⍵
    0.07
    Cont
    0.07
    ysics
    0.07
    QtCore
    0.07
    productName
    0.07
     PI
    0.07
    �
    0.07
    	BOOST
    0.07
    Act Density 0.005%

    No Known Activations