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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ar
    -0.07
    ocracy
    -0.07
    ('(
    -0.07
    -blue
    -0.06
     VIS
    -0.06
    demo
    -0.06
    expand
    -0.06
    ales
    -0.06
    377
    -0.06
     تمامی
    -0.06
    POSITIVE LOGITS
     softened
    0.06
     отв
    0.06
     sovereign
    0.06
     transforming
    0.06
    DW
    0.06
     soften
    0.05
     Ogre
    0.05
    aviour
    0.05
     Sergio
    0.05
     UPDATE
    0.05
    Act Density 0.003%

    No Known Activations