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

    Neuronpedia

    INDEX
    Explanations

    methods and types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Test
    -0.07
     Пло
    -0.07
     Lovely
    -0.07
    (Test
    -0.06
    _TRANSL
    -0.06
     buena
    -0.06
     Arbitrary
    -0.06
    livě
    -0.06
     rob
    -0.06
     nic
    -0.06
    POSITIVE LOGITS
     الث
    0.06
    “그
    0.06
    _xpath
    0.06
     invitations
    0.06
     Sb
    0.06
     stared
    0.06
    �
    0.06
    -five
    0.05
    preneur
    0.05
    LineWidth
    0.05
    Act Density 0.114%

    No Known Activations