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

    Neuronpedia

    INDEX
    Explanations

    st

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     triangles
    -0.07
     цвет
    -0.07
    围
    -0.06
    овый
    -0.06
     achieved
    -0.06
    ynchronization
    -0.06
    rito
    -0.06
    -eyed
    -0.06
     optimization
    -0.06
     Kelley
    -0.06
    POSITIVE LOGITS
    apg
    0.07
    ?a
    0.07
    (deg
    0.06
    �
    0.06
    BootTest
    0.06
     ancest
    0.06
     Depart
    0.06
    irectional
    0.06
    	HANDLE
    0.06
    ,long
    0.06
    Act Density 0.002%

    No Known Activations