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
    entialAction
    -0.07
    etta
    -0.06
     dieta
    -0.06
    clip
    -0.06
     并
    -0.06
    OTES
    -0.06
    щий
    -0.06
    ksiyon
    -0.06
     CPA
    -0.06
     problémy
    -0.06
    POSITIVE LOGITS
     nevid
    0.06
     =>{↵
    0.06
     prosecuting
    0.06
     Ag
    0.06
    ्म
    0.06
    .Bundle
    0.06
     super
    0.06
    ]++;↵
    0.06
     Dak
    0.06
     ответствен
    0.06
    Act Density 0.016%

    No Known Activations