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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pwd
    -0.06
     expiry
    -0.06
    اپیم
    -0.06
    	e
    -0.06
     �
    -0.06
    іст
    -0.06
    _From
    -0.06
    лас
    -0.05
    الف
    -0.05
    info
    -0.05
    POSITIVE LOGITS
    logout
    0.07
     IGN
    0.07
     вступ
    0.07
     SqlConnection
    0.06
     capture
    0.06
     Publication
    0.06
    yth
    0.06
     tad
    0.06
     Ukrain
    0.06
     فيه
    0.06
    Act Density 0.035%

    No Known Activations